[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6KS8GZK4RSM25NEVE78MMSE":3,"skill-same:01M6KS8GZK4RSM25NEVE78MMSE":65},{"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":18,"publishedAt":32,"linkOnly":33,"markdownContent":34,"markdownBody":35,"frontMatter":36,"refName":43,"commitSha":44,"skillDirectory":45,"forksCount":46,"repositoryHtmlUrl":47,"repositoryHomepageUrl":6,"ownerHtmlUrl":48,"ownerBlogUrl":6,"ownerDescription":49,"updatedAt":50,"install":51,"resources":64},"01M6KS8GZK4RSM25NEVE78MMSE","suggest-fixes",null,"Suggest concrete code fixes for SkillGuard security findings — generate remediation patches","openmaster-ai\u002Fskillguard-cli","openmaster-ai","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F269944371?v=4","01M6KS862ZX1BTMRHNSRN9AV4R","OpenMaster","01M6KS867SMAHB6VS0RKYAZ8ND",1,"MIT","https:\u002F\u002Fgithub.com\u002Fopenmaster-ai\u002Fskillguard-cli\u002Fblob\u002Fmaster\u002Fskills\u002Fsuggest-fixes\u002FSKILL.md",[],[19,20,21,22,23,24,25,26,27,28,29,30,31],"fixes","suggest fixes","security","generate","code","remediation","Bash","grep","read","write","edit","skillguard","for","2026-11-10 10:12:30",false,"---\ndescription: Suggest concrete code fixes for SkillGuard security findings — generate remediation patches\nallowed-tools:\n  - Bash\n  - Read\n  - Glob\n  - Grep\n  - Edit\n  - Write\n---\n\n# Suggest Fixes for SkillGuard Findings\n\nReads SkillGuard scan findings and generates concrete code fixes. Can either suggest fixes or directly apply them with user approval.\n\n## Usage\n\n1. Generate a JSON report:\n   ```bash\n   npx skillguard \u003Ctarget> --json report.json\n   ```\n\n2. Ask to fix the findings. Read the report and the source files to generate patches.\n\n## Fix Strategies by Dimension\n\n### Prompt Injection\n- Remove injection phrases from prompts\n- Use structured prompt templates instead of string concatenation\n- Remove zero-width characters with text sanitization\n\n### Permission Escalation\n- Remove `dangerouslyDisableSandbox` — run in sandbox\n- Replace `sudo` with user-level operations\n- Change `chmod 777` to `chmod 755` or `644`\n- Add `allowed-tools` to SKILL.md frontmatter\n\n### Data Exfiltration\n- Isolate env var reads from network requests\n- Add URL allowlists for outbound HTTP\n- Remove direct .env file reading — use injected env vars\n\n### Destructive Operations\n- Add path allowlist validation before `rm -rf`\n- Replace `git push --force` with `--force-with-lease`\n- Add confirmation prompts before destructive ops\n\n### Supply Chain\n- Pin dependency versions: `package@1.2.3` instead of `package`\n- Replace `curl | bash` with download-then-review-then-execute\n- Add `@sha256:` digests to Docker FROM statements\n\n### Code Security\n- Replace `shell=True` with `shell=False` and argument lists\n- Replace `eval()` with `JSON.parse()` or safe alternatives\n- Use parameterized SQL queries instead of f-strings\n\n### Credential Leaks\n- Move hardcoded secrets to environment variables\n- Add `.env` to `.gitignore`\n- Replace hardcoded API keys with `process.env.KEY_NAME`\n\n### Least Privilege\n- Add `allowed-tools` frontmatter listing only needed tools\n- Split skills with shell+network+write into focused sub-skills\n\n### License Compliance\n- Check dependency license compatibility\n- Add license declarations to SKILL.md frontmatter\n\n### Resource Abuse\n- Add `maxIterations` or timeout to loops\n- Set reasonable retry limits with exponential backoff\n- Add recursion depth limits\n\n## Workflow\n\n1. Read the JSON report to identify findings\n2. Read each affected source file\n3. For each finding, propose a minimal, targeted fix\n4. Apply fixes with Edit tool (with user approval)\n5. Re-run `npx skillguard \u003Ctarget>` to verify the fix reduced the risk score\n","# Suggest Fixes for SkillGuard Findings\n\nReads SkillGuard scan findings and generates concrete code fixes. Can either suggest fixes or directly apply them with user approval.\n\n## Usage\n\n1. Generate a JSON report:\n   ```bash\n   npx skillguard \u003Ctarget> --json report.json\n   ```\n\n2. Ask to fix the findings. Read the report and the source files to generate patches.\n\n## Fix Strategies by Dimension\n\n### Prompt Injection\n- Remove injection phrases from prompts\n- Use structured prompt templates instead of string concatenation\n- Remove zero-width characters with text sanitization\n\n### Permission Escalation\n- Remove `dangerouslyDisableSandbox` — run in sandbox\n- Replace `sudo` with user-level operations\n- Change `chmod 777` to `chmod 755` or `644`\n- Add `allowed-tools` to SKILL.md frontmatter\n\n### Data Exfiltration\n- Isolate env var reads from network requests\n- Add URL allowlists for outbound HTTP\n- Remove direct .env file reading — use injected env vars\n\n### Destructive Operations\n- Add path allowlist validation before `rm -rf`\n- Replace `git push --force` with `--force-with-lease`\n- Add confirmation prompts before destructive ops\n\n### Supply Chain\n- Pin dependency versions: `package@1.2.3` instead of `package`\n- Replace `curl | bash` with download-then-review-then-execute\n- Add `@sha256:` digests to Docker FROM statements\n\n### Code Security\n- Replace `shell=True` with `shell=False` and argument lists\n- Replace `eval()` with `JSON.parse()` or safe alternatives\n- Use parameterized SQL queries instead of f-strings\n\n### Credential Leaks\n- Move hardcoded secrets to environment variables\n- Add `.env` to `.gitignore`\n- Replace hardcoded API keys with `process.env.KEY_NAME`\n\n### Least Privilege\n- Add `allowed-tools` frontmatter listing only needed tools\n- Split skills with shell+network+write into focused sub-skills\n\n### License Compliance\n- Check dependency license compatibility\n- Add license declarations to SKILL.md frontmatter\n\n### Resource Abuse\n- Add `maxIterations` or timeout to loops\n- Set reasonable retry limits with exponential backoff\n- Add recursion depth limits\n\n## Workflow\n\n1. Read the JSON report to identify findings\n2. Read each affected source file\n3. For each finding, propose a minimal, targeted fix\n4. Apply fixes with Edit tool (with user approval)\n5. Re-run `npx skillguard \u003Ctarget>` to verify the fix reduced the risk score\n",{"description":7,"allowed-tools":37},[25,38,39,40,41,42],"Read","Glob","Grep","Edit","Write","master","9fd25469bd9024221a0dad7180338fc69731525c","skills\u002Fsuggest-fixes",0,"https:\u002F\u002Fgithub.com\u002Fopenmaster-ai\u002Fskillguard-cli","https:\u002F\u002Fgithub.com\u002Fopenmaster-ai","One Platform. Every Master.","2026-04-04 14:32:39",{"source":8,"skillName":5,"commands":52,"prompt":62,"zipAvailable":63},[53,56,59],{"tool":54,"command":55},"npx","npx skills add openmaster-ai\u002Fskillguard-cli --skill suggest-fixes",{"tool":57,"command":58},"bunx","bunx skills add openmaster-ai\u002Fskillguard-cli --skill suggest-fixes",{"tool":60,"command":61},"pnpm","pnpm dlx skills add openmaster-ai\u002Fskillguard-cli --skill suggest-fixes","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fopenmaster-ai\u002Fskillguard-cli\u002Fblob\u002Fmaster\u002Fskills\u002Fsuggest-fixes\u002FSKILL.md",true,[],[66,82,105],{"skillNo":67,"name":68,"nameZh":6,"description":69,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":70,"categories":71,"keywords":77,"publishedAt":32},"01M6KS8M67XTSF6T078R7NBKCC","sample-skill","Test skill for SkillGuard","https:\u002F\u002Fgithub.com\u002Fopenmaster-ai\u002Fskillguard-cli\u002Fblob\u002Fmaster\u002Ftests\u002Ffixtures\u002Fsample-skill\u002FSKILL.md",[72],{"categoryNo":73,"categoryName":74,"taxonomyType":75,"taxonomyTypeDesc":76},"01JBSEEDCAT000000000000023","Skill与智能体开发","SCENARIO","使用场景",[78,79,80,81,25,27,30,31],"sample","sample skill","test","Test Skill",{"skillNo":83,"name":84,"nameZh":6,"description":85,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":86,"categories":87,"keywords":93,"publishedAt":32},"01M6KS8DG69PJPT7CSNPK26J6J","explain-report","Explain a SkillGuard security audit report — analyze findings, assess real risk vs false positives, and provide context","https:\u002F\u002Fgithub.com\u002Fopenmaster-ai\u002Fskillguard-cli\u002Fblob\u002Fmaster\u002Fskills\u002Fexplain-report\u002FSKILL.md",[88],{"categoryNo":89,"categoryName":90,"taxonomyType":91,"taxonomyTypeDesc":92},"01JBSEEDCAT000000000000034","行政与办公人员","PROFESSION","适用职业",[94,95,96,25,97,98,26,27,99,30,100,101,102,21,103,104],"explain","report","explain report","risk","analyze","context","false","assess","security audit","audit","audit report",{"skillNo":106,"name":103,"nameZh":6,"description":107,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":108,"categories":109,"keywords":110,"publishedAt":32},"01M6KS88MBRYZ2M8TZSYPVV8GQ","Run SkillGuard security audit on AI agent skills — scans 10 dimensions with 109 rules based on OWASP LLM Top 10, SLSA, and Google SAIF","https:\u002F\u002Fgithub.com\u002Fopenmaster-ai\u002Fskillguard-cli\u002Fblob\u002Fmaster\u002Fskills\u002Faudit\u002FSKILL.md",[],[103,27,21,111,112,113,114,115,102,25,116,30,117,118,119,120],"ai agent","owasp llm","run","owasp","slsa","Rules","dimensions","with","top","google"]