agent-skill-kit-security-auditor
Audit a skills tree for the four canonical security findings — unauthorized frontmatter fields, command-injection patterns in scripts, unvetted cross-repo dependency origins, and host-path leaks in body or scripts. Use when the user asks to audit, scan, security-check, or harden a skill or skills directory.
- License 许可
- Apache-2.0
- 最近更新
- 2026-08-25
- Stars
- ★ 0
- Forks
- 0
01 前言 Front Matter
- name
- agent-skill-kit-security-auditor
- tier
- org
- license
- Apache-2.0
- description
- Audit a skills tree for the four canonical security findings — unauthorized frontmatter fields, command-injection patterns in scripts, unvetted cross-repo dependency origins, and host-path leaks in body or scripts. Use when the user asks to audit, scan, security-check, or harden a skill or skills directory.
- compatibility
- requires `skills-ref` CLI; reads files only — no network, no exec
03 SKILL.md 正文
Agent Skill Security Auditor
Wraps the skills-ref audit CLI. Runs four independent passes and emits severity-graded findings (HIGH / MEDIUM / LOW). Exits non-zero on any HIGH, or on any MEDIUM when --strict is passed.
When to use
- Before merging any change under
.agents/skills/. - During CI on every PR touching skills or their
scripts/dirs. - After importing skills from a third-party repository.
- During incident response when investigating a suspected supply-chain compromise.
Invocation
skills-ref audit <root> [--format json|human] [--strict] [--allowed-origins a,b] [--skip frontmatter|scripts|deps|path-leak]
Findings
| Code | Severity | Trigger |
|---|---|---|
A001_UNAUTHORIZED_FIELD |
MEDIUM | Top-level frontmatter key not in the spec allowlist. |
A010_COMMAND_INJECTION_PATTERN |
HIGH | eval(, exec(, subprocess(...,shell=True), os.system(, backticks. |
A020_UNVETTED_ORIGIN |
MED/HIGH | Cross-repo dep owner outside --allowed-origins (HIGH when list is set). |
A030_HOST_PATH_LEAK |
MEDIUM | /Users/, /home/, or /tmp/ literal in body or scripts (with carve-outs for fenced bash/console/text blocks and blockquote lines). |
Exit codes
| Code | Meaning |
|---|---|
| 0 | No HIGH findings (and no MEDIUM when --strict is set). |
| 1 | At least one HIGH (or any MEDIUM when --strict). |
Pass-level skipping
--skip frontmatter,scripts,deps,path-leak disables individual passes. Useful when one pass has known noise that must be triaged before re-enabling.
Reference
The auditor is implemented twice — .agents/skills/agent-skill-kit-commons/packages/mjs/ and .agents/skills/agent-skill-kit-commons/packages/py/ — and shares one injection-pattern table at .agents/skills/agent-skill-kit-commons/packages/mjs/assets/injection_patterns.json (symlinked into py). The fixture suite lives under .agents/skills/agent-skill-kit-commons/fixtures/audit/.
04 同仓库更多 Skills
validation_handoff
Forces the agent to conclude its response by generating a strict validation checklist and outlining pending actions, focusing heavily on defensive execution and edge-case testing.
project-ployglot-project-scafford
Scaffold a polyglot library project as TypeScript + Python twin packages under `packages/ts/` + `packages/py/`, with a shared `SPEC.md`, cross-language `tests/parity/fixtures.json`, side-by-side `examples/sdk/` + `examples/api/` documentation, per-package `Makefile`, and a root orchestrator that exposes `make ci`. Open-source friendly — no organization-specific paths or scopes baked in. Use when starting a new polyglot library, porting a single-language library to a twin, or auditing/regularizing an existing two-language repo against the canonical layout.
playwright-ui-locator
Auto-heal Playwright tests after a frontend developer changes a div's class, id, or other selector. Catches a failing Playwright test, captures the old vs new DOM tree, finds the element that drifted, derives the most stable replacement locator, and proposes the fix as a GitHub pull request (confident heals) or files a GitHub issue (ambiguous / element-removed cases) — never editing the working tree directly. Trigger when Playwright tests fail with "locator resolved to 0 elements", "Timeout waiting for selector", or after a UI refactor / class rename / Tailwind cleanup broke previously-passing tests.
org-learn-context-window
Distill the current conversation into a reusable command or skill artifact. Use when the user wants to capture a workflow they just executed (create a reusable slash command) or formalize a resolution/mistake/correction into a reusable skill so the same class of issue never recurs.
org-agent-skill-creator
Scaffold and validate scope-aware agent skills (company, enterprise, org, team, project, application). Use when the user asks to create a new agent skill, generate a SKILL.md file, scaffold a skill directory, or validate that existing skill directories meet SKILL_SPEC.md (frontmatter, naming rules, structure, scope/tier).
app-workshop-session-pdf-recap-next
Extract content from a workshop session PDF and produce a structured recap focused on (1) what was learned, (2) next steps, and (3) possible enhancements. Ingests a single PDF file path, parses session material (slides, transcripts, exercises, Q&A), and emits a Markdown report with Learning Recap, Next Steps, and Enhancement Opportunities sections with page-level traceability. Use when the user asks to "summarize a workshop", "recap a training PDF", "pull next steps from a session deck", or provides a workshop/seminar/tutorial PDF and wants a learn-and-act summary.