skill-vetter

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

• Third-party content exposure detected (high risk: 0.90). This skill's SKILL.md explicitly instructs the agent to fetch and read repository contents from public third-party sources (e.g., the "Quick Vet Commands" that curl https://api.github.com and https://raw.githubusercontent.com and Step 2's "Read ALL files in the skill"), so untrusted user-generated content from GitHub/ClawdHub will be ingested and used to make install/permission decisions.