ingest-yt-history
Warn
Audited by Snyk on Mar 17, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 0.80). The skill explicitly calls the YouTube Data API to fetch public, user-generated metadata (see src/enrich.py and sanity/youtube_api.py invoked by the "enrich" command in run.sh and SKILL.md), and that untrusted data (titles, tags, channel info) is parsed and used by find_music, taxonomy extraction, and memory sync to drive decisions and persona behavior—so third-party content can materially influence actions.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata