Farcaster Social Protocol Handler

Pass

Audited by Gen Agent Trust Hub on Aug 3, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: Communicates with the Neynar API at api.neynar.com to manage decentralized social content. This is a well-known service provider for the Farcaster protocol and represents the primary intended function of the skill.
  • [CREDENTIALS_UNSAFE]: Correctly instructs the user to manage NEYNAR_API_KEY and NEYNAR_SIGNER_UUID via environment variables rather than hardcoding them in scripts, following standard secret management practices.
  • [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection due to its core function of ingesting data from external, untrusted sources.
  • Ingestion points: Data enters the agent context through CastManager.search_casts, CastManager.lookup_cast, and FrameHandler.fetch_frame_metadata, which retrieve user-generated text and web metadata.
  • Boundary markers: The skill does not implement specific delimiters or 'ignore' instructions when returning external social media content to the agent.
  • Capability inventory: The skill possesses significant interactive capabilities, including the ability to publish new posts (publish_cast), delete content (delete_cast), and perform social reactions (like_cast, recast).
  • Sanitization: Content is parsed using standard JSON and HTML libraries; however, there is no validation or filtering of the natural language content to prevent embedded instructions from influencing agent behavior.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 3, 2026, 07:53 PM
Security Audit — agent-trust-hub — Farcaster Social Protocol Handler