use-skill

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

• Third-party content exposure detected (medium risk: 0.30). The agent fetches and executes arbitrary GitHub repository contents and linked skills via user-provided GitHub URLs.

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

• Potentially malicious external URL detected (high risk: 0.70). The skill fetches and executes GitHub-linked skills using arbitrary user-selected GitHub repositories via the gh CLI, presenting an unverified runtime external dependency with weak/unknown provenance.