Skill of Skills
📚 resourceActiveCuratedmedium

skills

by trailofbits

Supercharge your AI agents/bots with reusable skills

Stars

5.7k

Skill Type

🔍 Code Quality & Review

Quality Score

132/200

License

MIT

Forks

495

Last Updated

Jun 11, 2026

Discovered

Feb 4, 2026

Validation

Passed

github.com/trailofbits/skills

Quality Breakdown

132/ 200

Content Signals

○Gotchas/Edge Cases+40
✓Progressive Disclosure+30
○Trigger Description+20
✓Verification/Safety+20
✓Code Examples+15
✓Composability+15

Repo Health

✓Recent Activity+15
✓Scripts/Automation+10
✓Real Usage (Issues)+10
✓Single Responsibility+10
✓Config/Persistence+10
✓Install Instructions+5

Multi-platform bonus: +5 pts if tool supports 2+ platforms. Score derived from 12 structural signals — not stars or popularity.

Trust & Verification

medium

Requires extended permissions (shell access, subagents). Review before use.

Active

Updated within the last 90 days. Actively maintained.

Unverified skill. Always review source code before installing any skill from an unknown author.

Risk Assessment

  • Contains install scripts (.codex/scripts/install-for-codex.sh) that execute during setup, modifying local Codex configuration
  • Large collection of security audit and vulnerability scanning skills could enable offensive security activities if misused
  • Multiple blockchain vulnerability scanners (Solana, Cosmos, Algorand, Cairo, Substrate, TON) included
  • Agentic-actions-auditor skill contains detailed references to GitHub Actions injection vectors and exploitation techniques
  • CLAUDE.md persistent configuration file suggests persistent agent memory/instruction modification
  • Python validation scripts in .github/scripts could be entry points for bootstrap automation