fxmacrodata-calendar

Pass

Audited by Gen Agent Trust Hub on Jul 21, 2026

Risk Level: SAFE
Full Analysis
  • [COMMAND_EXECUTION]: The skill executes a Python script (fetch_calendar.py) that uses urllib.request to communicate with the official api.fxmacrodata.com endpoint. This is standard functionality for its stated purpose.
  • [DATA_EXFILTRATION]: The skill uses a sensitive API key (FXMACRODATA_API_KEY) to authenticate requests. However, it implements robust redaction logic in its _redact function to prevent the key from appearing in error messages or logs. Network traffic is restricted to the canonical API endpoint.
  • [PROMPT_INJECTION]: Instructions in SKILL.md are purely technical and do not contain any patterns attempting to override agent behavior or bypass safety filters. It provides clear guidance for the agent to incorporate macro data into trade plans.
  • [EXTERNAL_DOWNLOADS]: The script fetches data from a well-known financial data service (fxmacrodata.com). The script includes rigorous validation for the incoming JSON data, specifically checking for non-finite numbers (NaN/Infinity) and enforcing strict typing for data quality markers (is_official, point_in_time_safe, etc.) to ensure analysis readiness.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 21, 2026, 10:06 AM
Security Audit — agent-trust-hub — fxmacrodata-calendar