farcaster
Warn
Audited by Snyk on Feb 20, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 0.90). This skill fetches user-generated Farcaster content from the public Neynar API (see SKILL.md and index.ts handlers like handleFeed, handleSearch, handleTrending and the tool definitions such as farcaster_search/farcaster_trending), and the agent reads that untrusted third-party content and can perform actions (post/like/recast/follow), so injected instructions in casts could materially influence behavior.
Audit Metadata