swing-trading

Pass

Audited by Gen Agent Trust Hub on Sep 3, 2026

Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The workflow involves running a local Python script (scripts/swing_trading_diagnostics.py) to generate performance metrics. The execution is restricted to local processing of a user-provided CSV file.\n- [INDIRECT_PROMPT_INJECTION]: The skill processes external data via a CSV file, which serves as an ingestion point for untrusted content.\n
  • Ingestion points: input.csv read by scripts/swing_trading_diagnostics.py.\n
  • Boundary markers: Not present in the script or prompt workflow.\n
  • Capability inventory: The script is limited to file I/O for reading CSV and writing JSON; it contains no network operations, subprocess calls, or dynamic code execution.\n
  • Sanitization: The script performs type validation by coercing trade data into numeric and datetime formats before processing.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 3, 2026, 08:46 AM
Security Audit — agent-trust-hub — swing-trading