skill-downloader

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

• Third-party content exposure detected (medium risk: 0.30). The workflow downloads and reads GitHub repositories and skill packages authored by third parties, exposing the agent to untrusted external text during skill installation and validation.

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

• Potentially malicious external URL detected (high risk: 0.70). The skill contains scripts that accept arbitrary user-supplied URLs to download and install archives or git repositories at runtime without verification or pinning, constituting an operational dependency on external sources.