cross-venue-crypto-mm
Pass
Audited by Gen Agent Trust Hub on Sep 18, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill provides a legitimate framework for financial market making research and diagnostics without any detected malicious patterns or behaviors.
- [INDIRECT_PROMPT_INJECTION]: The skill processes external data from CSV files using
scripts/cross_venue_crypto_mm_diagnostics.py. While this defines an attack surface for indirect prompt injection via untrusted data ingestion, the script implements strong type enforcement usingpd.to_numericandpd.to_datetimewitherrors='coerce', which ensures that only valid data is processed and summarized for the agent, effectively mitigating the risk of instructions leaking through data fields.
Audit Metadata