fundamentals

Pass

Audited by Gen Agent Trust Hub on Sep 19, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill processes financial data from Yahoo Finance, which is a standard surface for indirect prompt injection.
  • Ingestion points: Data is fetched from Yahoo Finance via the trading_skills library in the scripts fundamentals.py and piotroski.py.
  • Boundary markers: The output is structured as JSON but does not use specific delimiters to protect against instructions embedded in external data.
  • Capability inventory: The skill scripts are limited to data retrieval and analysis; they do not have network exfiltration or system modification capabilities.
  • Sanitization: Input ticker symbols are converted to uppercase before use.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 19, 2026, 05:56 PM
Security Audit — agent-trust-hub — fundamentals