creator-teardown

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

• Third-party content exposure detected (medium risk: 0.30). The skill workflow consumes public TikTok, YouTube, and Instagram video profiles and pasted video links via yt-dlp and user input without pre-filtering, exposing the agent to outsider-authored free text.

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

• Potentially malicious external URL detected (high risk: 0.70). The skill's setup reference documents an official installation command pulling Homebrew from https://raw.githubusercontent.com/Homebrew/install/HEAD/install.sh, but that URI is an operational setup path delivering executable/install material under our dependency gate and weak provenance rules.