subtitles

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

• Third-party content exposure detected (low risk: 0.10). The agent fetches YouTube video transcripts from transcriptapi.com, which can contain user- or outsider-submitted video captions and titles.

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

• Potentially malicious external URL detected (high risk: 0.70). The skill relies on transcriptapi.com for authentication, account creation, and transcript retrieval, but this third-party service lacks established organizational provenance or independent cryptographic verification, making it an unknown external dependency.