neynar

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

• Third-party content exposure detected (high risk: 0.90). The skill's CLI (scripts/neynar.sh) explicitly fetches public, user-generated Farcaster content via Neynar API endpoints (e.g., cmd_feed -> /feed/user/casts, cmd_search -> /cast/search, cmd_cast -> /cast) and reads/outputs that content as part of normal workflow (searching, viewing feeds, then deciding to post/like/follow), so untrusted third‑party posts could indirectly influence agent behavior.