options-strategy-advisor
Pass
Audited by Gen Agent Trust Hub on Sep 15, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes data from the Financial Modeling Prep (FMP) API to calculate option prices and Greeks. While this introduces an ingestion point for external data, the risk is minimized by the skill's limited capabilities.
- Ingestion points: External data is fetched via
requests.getinscripts/black_scholes.pyto retrieve stock quotes, historical prices, and dividend information. - Boundary markers: None identified; the instructions do not include specific delimiters or warnings to ignore instructions embedded in the API data.
- Capability inventory: The skill is primarily focused on mathematical analysis using
numpyandscipy. It generates reports and ASCII diagrams. It does not possess capabilities for arbitrary command execution, network exfiltration of sensitive files, or persistence. - Sanitization: There is no explicit sanitization of the API response, but the logic processes the data numerically for financial formulas, which limits the potential for executing embedded prompts.
Audit Metadata