yield-curve-regime-detector
Pass
Audited by Gen Agent Trust Hub on Mar 10, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill is designed to run shell commands to manage environments and fetch financial data. Evidence in 'references/data-queries.md' shows commands for activating virtual environments, installing requirements from a relative path, and executing various Python scripts.
- [PROMPT_INJECTION]: The skill has an indirect prompt injection surface where user-provided inputs are used as command-line arguments. Ingestion points: The 'universe/tickers' confirmed in 'SKILL.md' Step 1. Boundary markers: None specified to protect against malicious input in the ticker strings. Capability inventory: Execution of Python scripts via the shell in 'references/data-queries.md'. Sanitization: No logic or instructions are provided to sanitize user input before passing it to the 'stock_data.py' or 'sec_edgar.py' scripts.
Audit Metadata