auto-skill-guide

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

• Third-party content exposure detected (low risk: 0.10). The skill documentation mentions searching for community skills via npx skills find "query" and installing them via npx skills add owner/repo, which allows fetching external community-authored packages/skills into the agent's environment.

MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).

• Potentially malicious external URL detected (medium risk: 0.30). The skill instructs installation of an npm package (@matrixy/auto-skill) from an individual-owned repository namespace, which constitutes an unofficial operational dependency.