algo-risk-test
Pass
Audited by Gen Agent Trust Hub on Apr 26, 2026
Risk Level: SAFE
Full Analysis
- [COMMAND_EXECUTION]: The skill generates a Python harness script (risk_test.py) and instructs the user to execute it via the terminal using the Bash tool. This is the primary function of the skill and is performed locally within the user's environment.- [DATA_EXPOSURE]: The skill demonstrates safe credential management by instructing the use of environment variables (OPENALGO_API_KEY) and .env files rather than hardcoding sensitive information.- [PROMPT_INJECTION]: The skill includes defensive instructions and pre-flight checks, explicitly requiring the user to verify the 'Sandbox Mode' status before proceeding to prevent accidental live trading.- [DYNAMIC_EXECUTION]: The generated script modifies the Python path (sys.path) to locate local dependencies within a specific project structure (.claude/skills/algo-expert/...). This is a common pattern for managing local assets in specialized development environments.
Audit Metadata