futures-position-sizer

Pass

Audited by Gen Agent Trust Hub on Sep 5, 2026

Risk Level: SAFE
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill ingests data from external JSON reports, but this surface is well-defended. 1. Ingestion point: scripts/futures_position_sizer.py (load_json_file). 2. Boundary markers: scripts/futures_sizing.py (normalize_gate_report) enforces strict schema validation. 3. Capability inventory: No network or shell execution; capabilities are limited to console logging and local file writes. 4. Sanitization: Strict alphanumeric regex, enums, and numeric bounds are applied to all external fields.
  • [COMMAND_EXECUTION]: The test suite uses subprocess.run to verify CLI behavior locally; this is a safe development practice and not an exploitable capability.
  • [EXTERNAL_DOWNLOADS]: Documentation references official exchange URLs for spec verification; no network requests are made during skill operation.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 5, 2026, 05:42 PM
Security Audit — agent-trust-hub — futures-position-sizer