ito-market-intelligence

Pass

Audited by Gen Agent Trust Hub on Sep 12, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process data from external, untrusted sources such as prediction market venues, social media, and general web data.\n
  • Ingestion points: Venue documentation, APIs (Polymarket, Kalshi, Itô), X, Exa, GitHub, and web search results as specified in SKILL.md.\n
  • Boundary markers: The skill includes guardrails instructing the agent to treat source inputs as information to be verified and to separate facts from interpretation.\n
  • Capability inventory: The skill is configured for read-only market intelligence and text generation; it does not explicitly use tools for file system modifications or code execution.\n
  • Sanitization: The output contract mandates specific disclaimers and links to sources to ensure grounding and transparency.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 12, 2026, 03:41 PM
Security Audit — agent-trust-hub — ito-market-intelligence