The Agent Skills Directory

[COMMAND_EXECUTION]: The skill includes documentation for various security tools such as nmap, gobuster, sqlmap, and nuclei. These are provided as instructional examples for the agent to use during a security assessment.
[INDIRECT_PROMPT_INJECTION]: The skill outlines a process where the agent interacts with external targets and processes the results. This creates a surface where malicious content from a target could potentially influence the agent.
Ingestion points: Data returned from web enumeration tools (whatweb, wappalyzer), vulnerability scanners (nuclei, nikto), and directory brute-forcing tools.
Boundary markers: No specific delimiters or safety instructions are provided to the agent for handling tool output.
Capability inventory: The skill methodology involves executing local binary tools and performing network reconnaissance.
Sanitization: No explicit sanitization or filtering of external tool output is defined in the methodology.

pentest-expert