ito-market-intelligence
Pass
Audited by Gen Agent Trust Hub on Aug 7, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: No malicious patterns, obfuscation, or unauthorized access attempts were identified. The skill follows best-practices for read-only market intelligence.
- [PROMPT_INJECTION]: The instructions include robust guardrails that prevent the agent from providing investment advice or simulating live trades. The ingestion of external market data from sources like Polymarket and Kalshi presents a potential surface for indirect prompt injection; however, the skill lacks dangerous primitives or local execution capabilities that would make this surface exploitable.
- [CREDENTIALS_UNSAFE]: References to ITO_API_KEY indicate a requirement for standard API configuration; no hardcoded credentials, secrets, or exfiltration logic were found.
Audit Metadata