video-analysis

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

• Third-party content exposure detected (medium risk: 0.30). The workflow fetches external videos via links (using yt-dlp) and allows parsing external meeting transcripts containing outsider-authored free text, which are processed and consumed by the agent.

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

• Potentially malicious external URL detected (medium risk: 0.30). The installation instructions instruct the user to install a repository via npx skills add thatjuan/agent-skills --skill video-analysis, which is a common/reputable unofficial operational dependency.