security-pentest-recon-scan
Pass
Audited by Gen Agent Trust Hub on Sep 16, 2026
Risk Level: SAFE
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill provides installation instructions for well-known security tools (nuclei, amass, ffuf, httpx) from recognized public repositories. These instructions are documented for manual environment setup and are not executed by the agent.- [COMMAND_EXECUTION]: The skill enforces a 'wrapper-only' policy, prohibiting the AI agent from executing raw command-line tools. It mandates the use of pre-validated scripts that include rate limiting and safety flags to prevent tool misuse.- [INDIRECT_PROMPT_INJECTION]: The skill processes output from security scans. It addresses this vulnerability surface by requiring the use of a redaction SDK to filter sensitive data and explicitly prohibiting the reading of local secret files like .env or private keys.
Audit Metadata