crypto-market-neutral
Pass
Audited by Gen Agent Trust Hub on Sep 18, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill utilizes a local Python script (scripts/crypto_market_neutral_diagnostics.py) to automate the calculation of trading metrics such as signal correlation and maximum drawdown. This execution is a functional component of the skill for data processing.
- [INDIRECT_PROMPT_INJECTION]: The skill processes external CSV files, which is a potential surface for indirect prompt injection. 1. Ingestion points: Untrusted data enters via input.csv. 2. Boundary markers: No explicit delimiters or instructions are provided to the agent for data isolation. 3. Capability inventory: Local file read and write operations. 4. Sanitization: The diagnostics script coerces data to numeric and datetime types using pandas, mitigating script-level injection.
Audit Metadata