plex
Warn
Audited by Snyk on Mar 13, 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's watchlist command fetches items from the plex.tv cloud via python-plexapi (PlexClient.watchlist / SKILL.md and README watchlist sections), and SKILL.md explicitly uses those watchlist titles/metadata to drive follow-up actions (e.g., search RuTracker and send torrents), so untrusted third-party metadata from plex.tv can materially influence agent decisions and tool use.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata