senior-security
Fail
Audited by Gen Agent Trust Hub on Feb 16, 2026
Risk Level: HIGHPROMPT_INJECTIONCOMMAND_EXECUTIONEXTERNAL_DOWNLOADS
Full Analysis
- Indirect Prompt Injection (HIGH): The skill processes untrusted code from external paths. * Ingestion points:
security_auditor.py,threat_modeler.py, andpentest_automator.pyaccept path arguments. * Boundary markers: None identified. * Capability inventory: Local script execution and file-write access ('Automated fixes'). * Sanitization: None identified. - Command Execution (MEDIUM): The skill prompts execution of local Python scripts, npm commands, and deployment tools like docker and kubectl.
- Data Exposure (MEDIUM): The instructions require handling .env files which often contain sensitive credentials.
- Unverifiable Dependencies (MEDIUM): Relies on npm and pip for installing external packages without specified versions or sources.
Recommendations
- AI detected serious security threats
Audit Metadata