Static-analysis security scoreboard for public AI agent skills.
SKILL.md on GitHub.
No mocks, no seeds, no Math.random(). Re-scan cadence: 6 hours.
| Skill | Repository | Risk | Findings | Last scanned |
|---|---|---|---|---|
| Loading… | ||||
Skills whose risk score changed the most over the last 7 daily snapshots.
Paste a public github.com/.../SKILL.md URL. The scanner pulls the raw file and reports a risk score within a few minutes.
Every skill is scored as the sum of pattern weights, capped at 100. Each pattern can contribute at most three times per skill to keep large files from dominating. Categories: safe 0–20 low 21–40 moderate 41–60 high 61–80 critical 81–100.
Patterns and weights are published below; you can audit the regexes in scanners/patterns.js.
| Pattern | Category | Weight | What it catches |
|---|
Public repositories the crawler walks every 6 hours.
| Repository | Branch | Last fetched | Status | Skills found |
|---|---|---|---|---|
| Loading… | ||||