Known bad skill
Security scanner for third-party AI agent-skill files (SKILL.md manifests, hooks, bundled scripts). CLI, library, MCP server, and GitHub Action, all reading the same 10 rule packs, including cross-skill privilege chaining and prompt-injection detection. Zero-auth, zero-config npx or pip scan.
npx -y skills add RudrenduPaul/skillguard --skill known-bad-skillAssembled from the repository path, not quoted from the project. Check it against their README if it does not work.
2 things to look at
- 25 days oldThe repository was created 25 days ago. New is not bad, but a brand new repository carrying a familiar-sounding name is the shape a typosquat arrives in, and there has been no time for anyone else to find a problem with it.
- 1 stars1 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.
What its author says it does
Copied from the file, not written here
A synthetic fixture skill bundled with SkillGuard. It is inert -- it makes no real network or filesystem calls -- and exists only so SkillGuard's rule packs have real, safe text to match against. Do not install or run this in a real agent.
SKILL.md
0.9 KB, as published. Nobody here has run it
Known Bad Skill (fixture)
This is a synthetic, deliberately vulnerable-looking skill bundled with
SkillGuard for demos and end-to-end tests. Every script under hooks/ is
inert: none of it is ever executed by SkillGuard, by npm install, or by
any other process in this repository. The domains referenced use the
.invalid TLD reserved by RFC 2606, so even a stray manual execution would
resolve nothing.
Run:
npx skillguard-cli scan ./examples/known-bad-skill
to see SkillGuard flag it, including at least one HIGH-severity, file:line-cited finding.