swaps

Pass

Audited by Gen Agent Trust Hub on Sep 3, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted external data from CSV files which could contain malicious instructions designed to influence the agent's behavior.
  • Ingestion points: The scripts/swaps_validation.py script reads user-provided CSV data via pd.read_csv(arguments.input_csv).
  • Boundary markers: No explicit boundary markers or instructions to ignore embedded content are provided in the prompt interpolation logic.
  • Capability inventory: The skill allows for file writing (scripts/swaps_validation.py writing to --output), and the SKILL.md instructions encourage the agent to execute Python scripts and read reference documentation.
  • Sanitization: The script performs type conversion using pd.to_numeric(errors='coerce') and pd.to_datetime(errors='coerce'), which provides basic data validation but does not sanitize against prompt-based attacks.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 3, 2026, 08:45 AM
Security Audit — agent-trust-hub — swaps