[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6MES5JENQW4QFSS4TK2BF6R":3,"skill-same:01M6MES5JENQW4QFSS4TK2BF6R":131},{"skillNo":4,"name":5,"nameZh":6,"description":7,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":16,"categories":17,"keywords":23,"publishedAt":44,"linkOnly":45,"markdownContent":46,"markdownBody":47,"frontMatter":48,"refName":72,"commitSha":73,"skillDirectory":74,"forksCount":75,"repositoryHtmlUrl":76,"repositoryHomepageUrl":77,"ownerHtmlUrl":78,"ownerBlogUrl":79,"ownerDescription":80,"updatedAt":81,"install":82,"resources":94},"01M6MES5JENQW4QFSS4TK2BF6R","security",null,"Review code for security problems; scan for vulnerabilities, secrets, dependency and prompt risks. Use when: asked whether code is safe to ship, even one small handler.","hashgraph-online\u002Fawesome-codex-plugins","hashgraph-online","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F160371962?v=4","01M6CNB6NRJVNNGN14TR01Q6D3","HOL (Hashgraph Online)","01M6JT1HSKKG9V68KQAQGBA7XP",1575,"Apache-2.0","https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fboshu2\u002Fagentops\u002Fskills\u002Fsecurity\u002FSKILL.md",[18],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000023","Skill与智能体开发","SCENARIO","使用场景",[5,24,25,26,27,28,29,30,31,32,33,34,35,36,37,38,39,40,41,42,43],"write","when","supply","context","ship","supply-chain","canonical","handler","integrity","suite","safe","secrets","dependency","product","review","code","security scan","design","chain","sre","2026-11-10 10:12:30",false,"---\nname: security\ndescription: 'Review code for security problems; scan for vulnerabilities, secrets, dependency and prompt risks. Use when: asked whether code is safe to ship, even one small handler.'\npractices:\n- supply-chain-integrity\n- design-by-contract\n- sre\nhexagonal_role: driven-adapter\nconsumes:\n- repo-context\nproduces:\n- security-gate-summary.json\n- suite-summary.json\n- redteam-results.json\ncontext_rel:\n- kind: supplier-to\n  with: validate\nskill_api_version: 1\nuser-invocable: true\nmetadata:\n  capabilities: [security]\n  effects: [write_scan_artifacts]\n  canonical_status: canonical\n  disposition: keep_specialist\n  graph_root: true\n  tier: product\n  dependencies: []\noutput_contract: 'stdout: security scan report'\n---\n# Security Skill\n\n> **Purpose:** Find and report security weaknesses in code, scripts, authorized binaries, and repo-managed prompt surfaces, with honest coverage.\n\nUse this skill for a caller-requested security review of code or of a plan or design before code exists, a repository scan, authorized binary assurance, dependency risk, secrets, or offline prompt-surface redteam.\n\n## Critical Constraints\n\n- Scan only repositories, binaries, and prompt surfaces the operator owns or is explicitly authorized to assess. **Why:** a security review does not grant access to third-party systems or proprietary material.\n- Keep collection read-only by default; do not exfiltrate secrets, execute destructive payloads, or mutate policy\u002Fbaselines to manufacture green. **Why:** the assessment must not become the incident or erase its evidence.\n- Treat missing\u002Ferror scanners as a coverage gap, never a clean finding; use `--require-tools` when complete tool coverage is required. **Why:** absent evidence is not evidence of absence.\n- Use the current agent and local shell; do not start another runtime or orchestration substrate unless explicitly requested. **Why:** repository scanning is a bounded operation, not permission to fan out.\n- Report findings and coverage gaps, then stop. Remediation, risk acceptance,\n  reruns, promotion, and any ship or merge call are caller decisions. Asked\n  whether to ship, merge or deploy, give the findings and coverage, then say in\n  one line that the go\u002Fno-go on that evidence is the caller's; recommending\n  ship, hold or block in any wording is that decision. Name each finding's\n  remediation class in a few words; do not write the patch, a plan, an owner,\n  or a priority. An independent go\u002Fno-go on a security-boundary change is\n  [Validate](..\u002Fvalidate\u002FSKILL.md)'s.\n\n## What every review reports\n\nApply these to every review, scripted or manual. They are the rules most often skipped:\n\n1. **Fail-open paths.** For every guard, check, timeout, and exception handler\n   on the surface, ask what happens when it errors or hangs. A control that\n   grants access, skips a check, or continues as success on error is a finding\n   even when its happy path is correct.\n2. **Borrowed identity.** Trace the effective identity at each hop (user,\n   service, token, default, hook). A hop where identity is assumed, defaulted,\n   or inherited instead of verified is the **borrowed identity** failure mode\n   and a finding.\n3. **Per-class coverage ledger.** Walk every applicable class in\n   [the class checklist](references\u002Fowasp-checklist.md), plus fail-open,\n   identity and any class the surface needs that the list lacks, and give each\n   a result: finding, clean, or not assessed. An unvisited class is a gap, never a clean.\n   Chasing one lead to the exclusion of the taxonomy is the **first-scent\n   fixation** failure mode.\n4. **Proven versus suspected.** A finding is proven only when you ran a\n   concrete input, request, or command and observed the behavior; capture it.\n   A finding reasoned from the code is suspected, even with a candidate input;\n   give that input and rank it below proven findings.\n5. **Snapshot scope.** Name the exact snapshot (commit, working tree on a\n   stated HEAD, or document revision) and the path scope. List inputs you did\n   not read separately as unread, deleted or outside scope; none of them counts\n   as clean. Keep impact inside the snapshot: a finding that needs absent code,\n   a future change or an unread path is a hypothesis and is labeled so. When\n   the remaining budget cannot finish another full pass, stop opening new leads\n   and report the hunt as unconverged.\n6. **Shipped scope for a share or publish question.** When asked whether\n   content is safe to make public or hand to another party (a repository, an\n   export, a package), the snapshot is what the recipient will receive: the\n   built artifact or output tree, every commit reachable in the history that\n   travels with it, and derived copies such as indexes, caches and generated\n   files. Content removed at HEAD is still exposed in earlier commits. Report\n   history exposure with its fix class (credential rotation, fresh history or\n   an owner-authorized rewrite) and perform none of them.\n\nFor each finding, explain the attacker path and relevant protective control in\nthe fields below. Read [attacker-path evidence](references\u002Fattacker-path-evidence.md)\nonly when reachability, control effectiveness, or claimed test completion needs\ncloser support for that finding.\n\n```text\ntarget:   \u003Cpaths, endpoints, or binary>; authorization: \u003Cboundary>\nsnapshot: \u003Ccommit | working tree on HEAD | document revision>; unread: \u003Cpaths> | deleted: \u003Cpaths> | outside scope: \u003Cpaths>\nfindings: \u003Cid> \u003Cseverity> \u003Cfile:line> \u003Cclass>: \u003Cwhat>\n          proven: \u003Cinput run> | suspected: \u003Ccandidate input, why not run>\n          path: \u003Cattacker input> -> \u003Creachable behavior> -> \u003Ctrust boundary> -> \u003Cimpact>\n          control: \u003Crelevant protection challenged and outcome, or none identified>\n          fix class: \u003Ca few words>\ncoverage: \u003Cclass> -> finding \u003Cids> | clean | not assessed (\u003Cwhy>)\ntools:    \u003Cscanner or command> -> ran | missing | error\nhunt:     converged after \u003Cn> passes | unconverged | not run\n```\n\n## Manual hunt\n\nCode-level review and redteam passes work in any repository, with or without\nAgentOps tooling. Walk the ledger against the full surface and probe fail-open\nbehavior where that is safe. Repeat full passes until one complete pass adds no\nnew finding and no new coverage gap; that quiet round is the stop condition. If\nthe budget ends first, report the hunt as unconverged. The quiet-round rule\napplies only to the manual hunt.\n\nA plan, spec or design with no code yet gets the same hunt, aimed at what the\ndocument proposes. List the endpoints, data stores, integrations and inputs it\nadds, then report only weaknesses an attacker could use if it is built as\nwritten, such as a capability with no named actor or access decision; sensitive\ndata whose handling in transit, at rest, in logs or at deletion is unstated; a\nthird party or secret whose trust, storage, rotation or compromise behavior is\nunstated; or a stated choice, including how an input is handled, that is itself\nunsafe. Cite the section. A weakness in what the document proposes is inside\nits revision, not a rule-5 hypothesis; with nothing to run, each is suspected.\n\n## Scripted scans\n\nEach selected scan runs once per request; a rerun is a new caller decision.\n\n`\u003Cskill-dir>` is the directory that contains this SKILL.md. Claude Code shows it\nas \"Base directory for this skill\"; Codex lists this skill's SKILL.md path; in\nan AgentOps source checkout it is `skills\u002Fsecurity`. Replace `\u003Cskill-dir>` with\nthat absolute path before running a command. The working directory stays the\nuser's repository. If the host did not show where this skill is installed, use\nthe directory of the SKILL.md you read. If you cannot determine it, do not guess\na path or run a same-named script from the current repository; say the bundled\nscript is unavailable and run the scanners the project already uses, record the\nsuite or redteam scan as a coverage gap, and do the manual hunt.\n\n| Surface | Entry point | Location |\n|---|---|---|\n| Repository gate (quick or full) | `bash scripts\u002Fsecurity-gate.sh` | AgentOps repository root only |\n| Composable suite for authorized binaries | `python3 \"\u003Cskill-dir>\u002Fscripts\u002Fsecurity_suite.py\"` | bundled with this skill |\n| Offline prompt-surface redteam | `python3 \"\u003Cskill-dir>\u002Fscripts\u002Fprompt_redteam.py\"` | bundled with this skill |\n\n- **No gate script** (any other repository): run the scanners the project\n  already uses, such as a dependency audit, secret scan, or static analyzer,\n  record each one that is absent as a coverage gap, and do the manual hunt.\n- **Redteam pack:** the bundled [attack pack](references\u002Fagentops-redteam-pack.json)\n  targets AgentOps control surfaces. In another repository its cases fail with\n  \"no files matched target globs\"; that is a pack mismatch, not a finding. A\n  PASS shows the controls are written down, not that an agent resists them.\n- Read [the suite runbook](references\u002Fsecurity-suite-runbook.md) before gate,\n  binary, policy, baseline, or redteam work. It holds the commands, the gate's\n  exit codes, the artifact contracts, and the limits of the dynamic run, which\n  is sampled and not isolated.\n\n### Triage\n\n1. Open the latest artifact and identify scanner, severity, file, and coverage gaps.\n2. Reproduce the finding with the narrowest safe command; an unreproduced hit stays suspected.\n3. Rank concrete findings and preserve coverage gaps.\n4. Stop. Remediation, risk acceptance, and any later scan are new caller decisions. Do not downgrade, suppress, or update a baseline merely to pass.\n\n## Output Specification\n\n- **Artifact directory:** suite and redteam runs write under their explicit\n  `--out-dir`; the repository gate's directory is in the runbook.\n- **Filename convention:** `security-gate-summary.json` (gate),\n  `suite-summary.json` (suite), `redteam\u002Fredteam-results.json` (redteam).\n- **Serialization\u002Fschema format:** JSON. **Validator command:** the gate\n  summary's field contract and `jq` check are in the runbook; a summary that\n  fails it makes the result incomplete.\n\n**Downstream handoff:** the review report above; for scripted scans also the\nartifact path, command and exit code, mode, and gate status. The\nreport stops after evidence: no owner, next action, approval, release, ship,\nor retry decision, and no newly exposed secret or unredacted sensitive payload.\n","# Security Skill\n\n> **Purpose:** Find and report security weaknesses in code, scripts, authorized binaries, and repo-managed prompt surfaces, with honest coverage.\n\nUse this skill for a caller-requested security review of code or of a plan or design before code exists, a repository scan, authorized binary assurance, dependency risk, secrets, or offline prompt-surface redteam.\n\n## Critical Constraints\n\n- Scan only repositories, binaries, and prompt surfaces the operator owns or is explicitly authorized to assess. **Why:** a security review does not grant access to third-party systems or proprietary material.\n- Keep collection read-only by default; do not exfiltrate secrets, execute destructive payloads, or mutate policy\u002Fbaselines to manufacture green. **Why:** the assessment must not become the incident or erase its evidence.\n- Treat missing\u002Ferror scanners as a coverage gap, never a clean finding; use `--require-tools` when complete tool coverage is required. **Why:** absent evidence is not evidence of absence.\n- Use the current agent and local shell; do not start another runtime or orchestration substrate unless explicitly requested. **Why:** repository scanning is a bounded operation, not permission to fan out.\n- Report findings and coverage gaps, then stop. Remediation, risk acceptance,\n  reruns, promotion, and any ship or merge call are caller decisions. Asked\n  whether to ship, merge or deploy, give the findings and coverage, then say in\n  one line that the go\u002Fno-go on that evidence is the caller's; recommending\n  ship, hold or block in any wording is that decision. Name each finding's\n  remediation class in a few words; do not write the patch, a plan, an owner,\n  or a priority. An independent go\u002Fno-go on a security-boundary change is\n  [Validate](..\u002Fvalidate\u002FSKILL.md)'s.\n\n## What every review reports\n\nApply these to every review, scripted or manual. They are the rules most often skipped:\n\n1. **Fail-open paths.** For every guard, check, timeout, and exception handler\n   on the surface, ask what happens when it errors or hangs. A control that\n   grants access, skips a check, or continues as success on error is a finding\n   even when its happy path is correct.\n2. **Borrowed identity.** Trace the effective identity at each hop (user,\n   service, token, default, hook). A hop where identity is assumed, defaulted,\n   or inherited instead of verified is the **borrowed identity** failure mode\n   and a finding.\n3. **Per-class coverage ledger.** Walk every applicable class in\n   [the class checklist](references\u002Fowasp-checklist.md), plus fail-open,\n   identity and any class the surface needs that the list lacks, and give each\n   a result: finding, clean, or not assessed. An unvisited class is a gap, never a clean.\n   Chasing one lead to the exclusion of the taxonomy is the **first-scent\n   fixation** failure mode.\n4. **Proven versus suspected.** A finding is proven only when you ran a\n   concrete input, request, or command and observed the behavior; capture it.\n   A finding reasoned from the code is suspected, even with a candidate input;\n   give that input and rank it below proven findings.\n5. **Snapshot scope.** Name the exact snapshot (commit, working tree on a\n   stated HEAD, or document revision) and the path scope. List inputs you did\n   not read separately as unread, deleted or outside scope; none of them counts\n   as clean. Keep impact inside the snapshot: a finding that needs absent code,\n   a future change or an unread path is a hypothesis and is labeled so. When\n   the remaining budget cannot finish another full pass, stop opening new leads\n   and report the hunt as unconverged.\n6. **Shipped scope for a share or publish question.** When asked whether\n   content is safe to make public or hand to another party (a repository, an\n   export, a package), the snapshot is what the recipient will receive: the\n   built artifact or output tree, every commit reachable in the history that\n   travels with it, and derived copies such as indexes, caches and generated\n   files. Content removed at HEAD is still exposed in earlier commits. Report\n   history exposure with its fix class (credential rotation, fresh history or\n   an owner-authorized rewrite) and perform none of them.\n\nFor each finding, explain the attacker path and relevant protective control in\nthe fields below. Read [attacker-path evidence](references\u002Fattacker-path-evidence.md)\nonly when reachability, control effectiveness, or claimed test completion needs\ncloser support for that finding.\n\n```text\ntarget:   \u003Cpaths, endpoints, or binary>; authorization: \u003Cboundary>\nsnapshot: \u003Ccommit | working tree on HEAD | document revision>; unread: \u003Cpaths> | deleted: \u003Cpaths> | outside scope: \u003Cpaths>\nfindings: \u003Cid> \u003Cseverity> \u003Cfile:line> \u003Cclass>: \u003Cwhat>\n          proven: \u003Cinput run> | suspected: \u003Ccandidate input, why not run>\n          path: \u003Cattacker input> -> \u003Creachable behavior> -> \u003Ctrust boundary> -> \u003Cimpact>\n          control: \u003Crelevant protection challenged and outcome, or none identified>\n          fix class: \u003Ca few words>\ncoverage: \u003Cclass> -> finding \u003Cids> | clean | not assessed (\u003Cwhy>)\ntools:    \u003Cscanner or command> -> ran | missing | error\nhunt:     converged after \u003Cn> passes | unconverged | not run\n```\n\n## Manual hunt\n\nCode-level review and redteam passes work in any repository, with or without\nAgentOps tooling. Walk the ledger against the full surface and probe fail-open\nbehavior where that is safe. Repeat full passes until one complete pass adds no\nnew finding and no new coverage gap; that quiet round is the stop condition. If\nthe budget ends first, report the hunt as unconverged. The quiet-round rule\napplies only to the manual hunt.\n\nA plan, spec or design with no code yet gets the same hunt, aimed at what the\ndocument proposes. List the endpoints, data stores, integrations and inputs it\nadds, then report only weaknesses an attacker could use if it is built as\nwritten, such as a capability with no named actor or access decision; sensitive\ndata whose handling in transit, at rest, in logs or at deletion is unstated; a\nthird party or secret whose trust, storage, rotation or compromise behavior is\nunstated; or a stated choice, including how an input is handled, that is itself\nunsafe. Cite the section. A weakness in what the document proposes is inside\nits revision, not a rule-5 hypothesis; with nothing to run, each is suspected.\n\n## Scripted scans\n\nEach selected scan runs once per request; a rerun is a new caller decision.\n\n`\u003Cskill-dir>` is the directory that contains this SKILL.md. Claude Code shows it\nas \"Base directory for this skill\"; Codex lists this skill's SKILL.md path; in\nan AgentOps source checkout it is `skills\u002Fsecurity`. Replace `\u003Cskill-dir>` with\nthat absolute path before running a command. The working directory stays the\nuser's repository. If the host did not show where this skill is installed, use\nthe directory of the SKILL.md you read. If you cannot determine it, do not guess\na path or run a same-named script from the current repository; say the bundled\nscript is unavailable and run the scanners the project already uses, record the\nsuite or redteam scan as a coverage gap, and do the manual hunt.\n\n| Surface | Entry point | Location |\n|---|---|---|\n| Repository gate (quick or full) | `bash scripts\u002Fsecurity-gate.sh` | AgentOps repository root only |\n| Composable suite for authorized binaries | `python3 \"\u003Cskill-dir>\u002Fscripts\u002Fsecurity_suite.py\"` | bundled with this skill |\n| Offline prompt-surface redteam | `python3 \"\u003Cskill-dir>\u002Fscripts\u002Fprompt_redteam.py\"` | bundled with this skill |\n\n- **No gate script** (any other repository): run the scanners the project\n  already uses, such as a dependency audit, secret scan, or static analyzer,\n  record each one that is absent as a coverage gap, and do the manual hunt.\n- **Redteam pack:** the bundled [attack pack](references\u002Fagentops-redteam-pack.json)\n  targets AgentOps control surfaces. In another repository its cases fail with\n  \"no files matched target globs\"; that is a pack mismatch, not a finding. A\n  PASS shows the controls are written down, not that an agent resists them.\n- Read [the suite runbook](references\u002Fsecurity-suite-runbook.md) before gate,\n  binary, policy, baseline, or redteam work. It holds the commands, the gate's\n  exit codes, the artifact contracts, and the limits of the dynamic run, which\n  is sampled and not isolated.\n\n### Triage\n\n1. Open the latest artifact and identify scanner, severity, file, and coverage gaps.\n2. Reproduce the finding with the narrowest safe command; an unreproduced hit stays suspected.\n3. Rank concrete findings and preserve coverage gaps.\n4. Stop. Remediation, risk acceptance, and any later scan are new caller decisions. Do not downgrade, suppress, or update a baseline merely to pass.\n\n## Output Specification\n\n- **Artifact directory:** suite and redteam runs write under their explicit\n  `--out-dir`; the repository gate's directory is in the runbook.\n- **Filename convention:** `security-gate-summary.json` (gate),\n  `suite-summary.json` (suite), `redteam\u002Fredteam-results.json` (redteam).\n- **Serialization\u002Fschema format:** JSON. **Validator command:** the gate\n  summary's field contract and `jq` check are in the runbook; a summary that\n  fails it makes the result incomplete.\n\n**Downstream handoff:** the review report above; for scripted scans also the\nartifact path, command and exit code, mode, and gate status. The\nreport stops after evidence: no owner, next action, approval, release, ship,\nor retry decision, and no newly exposed secret or unredacted sensitive payload.\n",{"name":5,"consumes":49,"metadata":51,"produces":58,"practices":62,"context_rel":65,"description":7,"hexagonal_role":69,"user-invocable":54,"output_contract":70,"skill_api_version":71},[50],"repo-context",{"tier":37,"effects":52,"graph_root":54,"disposition":55,"capabilities":56,"dependencies":57,"canonical_status":30},[53],"write_scan_artifacts",true,"keep_specialist",[5],[],[59,60,61],"security-gate-summary.json","suite-summary.json","redteam-results.json",[63,64,43],"supply-chain-integrity","design-by-contract",[66],{"kind":67,"with":68},"supplier-to","validate","driven-adapter","stdout: security scan report",1,"main","347aedf8480cd92b21f761e97b7343a45898f5fa","plugins\u002Fboshu2\u002Fagentops\u002Fskills\u002Fsecurity",491,"https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins","https:\u002F\u002Fhol.org\u002Fplugins\u002Fbest-codex-plugins","https:\u002F\u002Fgithub.com\u002Fhashgraph-online","https:\u002F\u002Fhol.org","Open-source standards and developer tools for interoperable AI agents: discovery, identity, communication, payments, privacy and security.","2026-11-14 14:06:13",{"source":8,"skillName":5,"commands":83,"prompt":93,"zipAvailable":54},[84,87,90],{"tool":85,"command":86},"npx","npx skills add hashgraph-online\u002Fawesome-codex-plugins --skill security",{"tool":88,"command":89},"bunx","bunx skills add hashgraph-online\u002Fawesome-codex-plugins --skill security",{"tool":91,"command":92},"pnpm","pnpm dlx skills add hashgraph-online\u002Fawesome-codex-plugins --skill security","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fboshu2\u002Fagentops\u002Fskills\u002Fsecurity\u002FSKILL.md",[95,101,105,109,113,117,123,127],{"path":96,"resourceType":97,"resourceTypeDesc":98,"sizeBytes":99,"sourceHtmlUrl":100},"references\u002Fagentops-redteam-pack.json","REFERENCE","参考文档",6571,"https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fboshu2\u002Fagentops\u002Fskills\u002Fsecurity\u002Freferences\u002Fagentops-redteam-pack.json",{"path":102,"resourceType":97,"resourceTypeDesc":98,"sizeBytes":103,"sourceHtmlUrl":104},"references\u002Fattacker-path-evidence.md",4829,"https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fboshu2\u002Fagentops\u002Fskills\u002Fsecurity\u002Freferences\u002Fattacker-path-evidence.md",{"path":106,"resourceType":97,"resourceTypeDesc":98,"sizeBytes":107,"sourceHtmlUrl":108},"references\u002Fowasp-checklist.md",6845,"https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fboshu2\u002Fagentops\u002Fskills\u002Fsecurity\u002Freferences\u002Fowasp-checklist.md",{"path":110,"resourceType":97,"resourceTypeDesc":98,"sizeBytes":111,"sourceHtmlUrl":112},"references\u002Fpolicy-example.json",525,"https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fboshu2\u002Fagentops\u002Fskills\u002Fsecurity\u002Freferences\u002Fpolicy-example.json",{"path":114,"resourceType":97,"resourceTypeDesc":98,"sizeBytes":115,"sourceHtmlUrl":116},"references\u002Fsecurity-suite-runbook.md",8575,"https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fboshu2\u002Fagentops\u002Fskills\u002Fsecurity\u002Freferences\u002Fsecurity-suite-runbook.md",{"path":118,"resourceType":119,"resourceTypeDesc":120,"sizeBytes":121,"sourceHtmlUrl":122},"scripts\u002Fprompt_redteam.py","SCRIPT","脚本",11577,"https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fboshu2\u002Fagentops\u002Fskills\u002Fsecurity\u002Fscripts\u002Fprompt_redteam.py",{"path":124,"resourceType":119,"resourceTypeDesc":120,"sizeBytes":125,"sourceHtmlUrl":126},"scripts\u002Fsecurity_suite.py",33494,"https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fboshu2\u002Fagentops\u002Fskills\u002Fsecurity\u002Fscripts\u002Fsecurity_suite.py",{"path":128,"resourceType":119,"resourceTypeDesc":120,"sizeBytes":129,"sourceHtmlUrl":130},"scripts\u002Fvalidate.sh",5521,"https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fboshu2\u002Fagentops\u002Fskills\u002Fsecurity\u002Fscripts\u002Fvalidate.sh",[132,142,150,158,166,174],{"skillNo":133,"name":134,"nameZh":6,"description":135,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":136,"licenseFileUrl":137,"sourceHtmlUrl":138,"categories":139,"keywords":140,"publishedAt":141},"01M7DV332YQMGD8WTRJ9DZQXTB","worktable-review-with-annotations","Create, inspect, reply to, update, or resolve situated Worktable annotations. Use when feedback belongs to a Doc section, block, text range, or HTML Doc, or when the user asks to address existing review feedback and coordinate a requested artifact edit.","MIT","https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fworktable\u002Fworktable-plugin\u002Fskills\u002Fworktable-review-with-annotations\u002FLICENSE","https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fworktable\u002Fworktable-plugin\u002Fskills\u002Fworktable-review-with-annotations\u002FSKILL.md",[],[],"2026-11-15 14:19:17",{"skillNo":143,"name":144,"nameZh":6,"description":145,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":136,"licenseFileUrl":146,"sourceHtmlUrl":147,"categories":148,"keywords":149,"publishedAt":141},"01M7DV2YGHCZVBEB1AHYB6CGHE","worktable-find-and-synthesize-context","Find, assess, and synthesize context from Worktable Docs and Records. Use when the user asks what a workspace contains, wants workspace-backed research, needs current facts reconciled across artifacts, or requests a cited synthesis without changing workspace state.","https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fworktable\u002Fworktable-plugin\u002Fskills\u002Fworktable-find-and-synthesize-context\u002FLICENSE","https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fworktable\u002Fworktable-plugin\u002Fskills\u002Fworktable-find-and-synthesize-context\u002FSKILL.md",[],[],{"skillNo":151,"name":152,"nameZh":6,"description":153,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":136,"licenseFileUrl":154,"sourceHtmlUrl":155,"categories":156,"keywords":157,"publishedAt":141},"01M7DV2TQN1H11ME2SAF9MXN7V","worktable-create-or-update-docs","Create, edit, rename, or maintain narrative Worktable Docs. Use for plans, decisions, briefs, notes, research syntheses, and other durable prose when the user requests a new artifact or a safe update to an existing one.","https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fworktable\u002Fworktable-plugin\u002Fskills\u002Fworktable-create-or-update-docs\u002FLICENSE","https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fworktable\u002Fworktable-plugin\u002Fskills\u002Fworktable-create-or-update-docs\u002FSKILL.md",[],[],{"skillNo":159,"name":160,"nameZh":6,"description":161,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":136,"licenseFileUrl":162,"sourceHtmlUrl":163,"categories":164,"keywords":165,"publishedAt":141},"01M7DV2NE452NEA8TXATKSNAJH","worktable-create-or-manage-records","Organize repeated structured information as durable Worktable Records. Use for research datasets, inventories, directories, pipelines, trackers, and other collections whose items need identity, fields, filtering, links, validation, or individual updates.","https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fworktable\u002Fworktable-plugin\u002Fskills\u002Fworktable-create-or-manage-records\u002FLICENSE","https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fworktable\u002Fworktable-plugin\u002Fskills\u002Fworktable-create-or-manage-records\u002FSKILL.md",[],[],{"skillNo":167,"name":168,"nameZh":6,"description":169,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":136,"licenseFileUrl":170,"sourceHtmlUrl":171,"categories":172,"keywords":173,"publishedAt":141},"01M7DV2HENRBR2KSCVM064WH0Y","worktable-create-or-manage-interactive-html","Create or improve durable visual and interactive artifacts in Worktable. Use for dashboards, trackers, calculators, mini apps, slide presentations, and other requests that benefit from a polished HTML Doc.","https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fworktable\u002Fworktable-plugin\u002Fskills\u002Fworktable-create-or-manage-interactive-html\u002FLICENSE","https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fworktable\u002Fworktable-plugin\u002Fskills\u002Fworktable-create-or-manage-interactive-html\u002FSKILL.md",[],[],{"skillNo":175,"name":176,"nameZh":6,"description":177,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":136,"licenseFileUrl":178,"sourceHtmlUrl":179,"categories":180,"keywords":181,"publishedAt":141},"01M7DV2CADR5R7RQFFYPNAGR9Y","worktable-collaborate-threads","Read, answer, and hand off messages through durable Worktable threads with users or other authenticated participants. Use when the user asks to check addressed messages, reply to a participant, continue a thread, request another agent's help, wait briefly for a response, or watch for comments and messages sent to the agent.","https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fworktable\u002Fworktable-plugin\u002Fskills\u002Fworktable-collaborate-threads\u002FLICENSE","https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fworktable\u002Fworktable-plugin\u002Fskills\u002Fworktable-collaborate-threads\u002FSKILL.md",[],[]]