ai-skill-auditor — independently scanned and version-tracked by SaferSkills.
SaferSkills independently audited ai-skill-auditor (Agent Skill) and scored it 65/100 (yellow). The audit ran 55 deterministic rules across Security, Supply Chain, Maintenance, Transparency, and Community; it found 4 high-severity and 0 lower-severity findings. The full rule-by-rule trace and per-finding evidence are below. Free, methodology-open.
Findings & checks · 4 flagged
The text {match} is the classic direct prompt-injection phrasing. Placed in a skill body that the agent reads as trusted instructions, it tries to make the agent abandon its prior rules and follow whatever comes next — a full system-prompt override.
ignore/disregard/forget … previous instructions sentence.The text {match} is the classic direct prompt-injection phrasing. Placed in a skill body that the agent reads as trusted instructions, it tries to make the agent abandon its prior rules and follow whatever comes next — a full system-prompt override.
ignore/disregard/forget … previous instructions sentence.Every scanned point with the score it earned and what moved between them.
First recorded scan — no prior version to compare against.
The primary manifest — the file an agent reads to learn what this artifact does.
ai-skill-auditorThis skill provides the AI Assistant the capability to automatically audit and review local code directories (such as other downloaded AI Skills) looking for standard malicious patterns (eval, destructive child_process, hidden HTTP requests) before running them.
When the user asks you to "audit a skill", "check a folder for security", or "verify the integrity of this downloaded repo":
run_command tool to execute the central audit script.node {workspaceRoot}/smartbrain-skill-auditor/bin/audit.js "C:/path/to/target/skill"node {workspaceRoot}/smartbrain-skill-auditor/bin/audit.js .~30 seconds. Free. No account. Every finding cites a rule and a line of evidence.