skill-vetter

MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).

• Third-party content exposure detected (high risk: 0.90). SKILL.md explicitly instructs the agent to fetch and read public GitHub/ClawdHub content (see "Quick Vet Commands" with curl calls to the GitHub API and raw.githubusercontent.com and "Step 2: Code Review" requiring reading all files), so untrusted user-generated third-party pages are ingested and used to drive vetting decisions—allowing indirect prompt injection.

MEDIUM W021: Hidden or invisible Unicode characters detected (potential obfuscation or prompt injection).

• Hidden Unicode characters detected (1 type(s) found)