market-breadth-analyzer

Pass

Audited by Gen Agent Trust Hub on May 12, 2026

Risk Level: SAFE
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill fetches market breadth data from CSV files hosted on 'tradermonty.github.io' (GitHub Pages). This is a well-known hosting service and the data is accessed via standard HTTP GET requests using the 'requests' library with appropriate timeouts.
  • [PROMPT_INJECTION]: The skill processes untrusted data from remote CSV files to generate reports for the agent. This represents an indirect prompt injection surface; however, the data is parsed into numeric values and specific categorical fields before being interpolated into structured templates, which limits the potential for embedded malicious instructions to influence the agent's behavior.
  • [COMMAND_EXECUTION]: There is no evidence of arbitrary command execution or unsafe subprocess calls. The skill performs localized mathematical calculations and file writing operations for reporting purposes.
  • [DATA_EXFILTRATION]: No sensitive data exposure or exfiltration patterns were detected. The skill only accesses the specific data URLs provided and does not attempt to read system secrets or environment variables.
Audit Metadata
Risk Level
SAFE
Analyzed
May 12, 2026, 08:40 AM
Security Audit — agent-trust-hub — market-breadth-analyzer