security-check
Pass
Audited by Gen Agent Trust Hub on Mar 17, 2026
Risk Level: SAFEPROMPT_INJECTIONCOMMAND_EXECUTIONEXTERNAL_DOWNLOADS
Full Analysis
- [PROMPT_INJECTION]: The skill analyzes untrusted source code and configuration files, presenting a surface for indirect prompt injection. Malicious instructions hidden in these files could attempt to influence the agent's behavior during the audit process.\n
- Ingestion points: Processes project files via Glob and Grep patterns in SKILL.md (e.g., .env, package.json, and various source code files).\n
- Boundary markers: No explicit markers or delimiters are defined to separate untrusted file content from the agent's instructions.\n
- Capability inventory: The skill can execute shell commands (Semgrep, Trivy, Gitleaks, Python scripts), write files, and use the gh CLI for network operations.\n
- Sanitization: There is no evidence of sanitization or filtering of the scanned content before the agent analyzes it.\n- [COMMAND_EXECUTION]: The skill runs external security binaries and local Python scripts (e.g., run_security_audit.py and generate_report.py) to perform automated security checks.\n- [EXTERNAL_DOWNLOADS]: The skill's installation process involves downloading its instruction file from a public GitHub repository using curl.
Audit Metadata