media-acquisition
Warn
Audited by Snyk on Aug 27, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (medium risk: 0.30). The skill runtime ingests only user-supplied URL/free-text as input to external “stock/archive/verify_clips” programs (e.g., the
[sourcing]sources “user URLs and licence-filtered search, needs yt-dlp”), so outsider-authored text can be POSTed/published into the provider feeds the workflow searches/reads and then passed into the pipeline without requiring the agent to pick a specific pre-identified item first.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata