muapi-youtube-shorts

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

• Third-party content exposure detected (low risk: 0.10). The skill processes arbitrary YouTube or video URLs via a remote AI clipping API, which may ingest untrusted video transcripts or metadata if treated as free-text input by the service, but fetching public URLs falls under the low-risk category where the agent actively selects specific content rather than monitoring an untrusted feed.