pangolin-strategy

Pass

Audited by Gen Agent Trust Hub on Apr 26, 2026

Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
  • [SAFE]: The skill follows established patterns for the Senpi platform, using the provided 'mcporter' CLI tool for all external interactions.
  • [COMMAND_EXECUTION]: The script 'scripts/pangolin_config.py' invokes the 'mcporter' tool via 'subprocess.run'. The implementation is secure as it avoids shell execution and uses structured arguments, preventing command injection.
  • [SAFE]: Usage of environment variables for wallet and strategy IDs is consistent with the platform's security model for managing trading credentials.
  • [SAFE]: Regarding indirect prompt injection, the skill ingests untrusted market data (ingestion points: 'scripts/pangolin-scanner.py' lines 173, 185) with no boundary markers. Capabilities include position creation and order cancellation via the 'mcporter' tool. Sanitization is performed via explicit type casting of external values.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 26, 2026, 05:44 AM