youtube-full

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

• Third-party content exposure detected (low risk: 0.10). The workflow fetches YouTube video transcripts, search results, and channel content via an external API where outsider-authored video text and descriptions are ingested upon explicit user or agent selection.

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

• Potentially malicious external URL detected (high risk: 0.70). The skill relies on runtime API calls to transcriptapi.com for its core behavior, which lacks established first-party enterprise provenance, resulting in an unverified third-party operational dependency.