skills/semgrep__skills
1
0
Fork 0
mirror of https://github.com/semgrep/skills.git synced 2026-09-20 14:21:26 +08:00
Code Issues Packages Projects Releases Wiki Activity
61 Commits 6 Branches 0 Tags
main
Commit Graph

14 Commits

Author SHA1 Message Date
Isaac Evans c011c534a1 Change title to 'Agent Skills [Beta]' 
Updated README to reflect beta status of agent skills.
 2026-02-05 08:57:18 -08:00
Drew Dennison 603e9e278f Fix install command to npx skills add semgrep/skills 
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
 2026-01-20 10:20:50 -08:00
Drew Dennison 0ee9a5f44a Standardize install command to npx skills semgrep/skills 
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
 2026-01-20 10:20:19 -08:00
Drew Dennison b9eac31076 Add semgrep skill for static analysis and custom rule creation 
Combines functionality from Trail of Bits' semgrep and semgrep-rule-creator skills:
- Running Semgrep scans with curated rulesets
- Creating custom detection rules with pattern matching and taint mode
- Test-driven rule development workflow
- CI/CD integration examples

Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
 2026-01-20 10:14:47 -08:00
Drew Dennison b8aa65bada Update installation command for skills 2026-01-20 09:52:19 -08:00
Drew Dennison 6befb8a586 Update README.md 2026-01-17 11:49:19 -08:00
Drew Dennison f99267b67e Update README.md 2026-01-17 11:48:33 -08:00
Drew Dennison 16ebae6d46 Update README.md 2026-01-17 11:47:59 -08:00
Drew Dennison 823e429b92 Add llm-security skill and make build tooling generic 
- Add llm-security skill covering OWASP Top 10 for LLM Applications 2025
  - 10 rules: Prompt Injection, Sensitive Disclosure, Supply Chain,
    Data Poisoning, Output Handling, Excessive Agency, System Prompt
    Leakage, Vector/Embedding Weaknesses, Misinformation, Unbounded
    Consumption
  - Python code examples with vulnerable/secure patterns

- Rename packages/code-security-build to packages/skill-build
  - Accept skill name as CLI argument: `pnpm validate llm-security`
  - Auto-discover skills with rules/ directories
  - Support Vulnerable/Secure labels (in addition to Incorrect/Correct)

- Update Makefile to build all skills automatically
  - `make validate` - validates all skills
  - `make build` - builds AGENTS.md for all skills
  - `make validate-skill SKILL=name` - single skill operations

- Update READMEs with llm-security documentation

Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
 2026-01-15 14:59:55 -08:00
Drew Dennison 5ad8da18da Update README with full list of security categories 
- Added all 28 security rule categories organized by impact level
- Listed supported languages (15+)
- Expanded use cases to include infrastructure configuration

Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
 2026-01-15 13:10:35 -08:00
Drew Dennison 1f11971e5a add an acknowledgement section 2026-01-15 13:03:50 -08:00
Drew Dennison c81e69ac77 first pass 2026-01-15 12:33:17 -08:00
Drew Dennison 4e9b382510 inital commit 2026-01-15 08:23:52 -08:00
Drew Dennison a09e9f1647 add readme 2026-01-14 20:56:50 -08:00