The Agent Skills Directory

[COMMAND_EXECUTION]: The skill instructions require the execution of various Nmap commands (nmap -sV, nmap -p-, nmap --script=vuln) to perform network scanning and service detection.
[INDIRECT_PROMPT_INJECTION]: The agent is instructed to parse and summarize output from network scans. Since this output originates from external, untrusted hosts (e.g., service banners, version strings), it could contain malicious instructions designed to influence the agent's behavior.
Ingestion points: Nmap scan results (XML files and terminal output) generated in step 2.
Boundary markers: The skill does not define specific delimiters or instructions to ignore embedded content within the scan results.
Capability inventory: The skill utilizes shell command execution via Nmap and Python.
Sanitization: No sanitization or filtering of the Nmap output is performed before the agent processes it into a summary table.
[DYNAMIC_EXECUTION]: Step 2 includes a Python one-liner (python3 -c) that dynamically executes code to convert XML data to JSON using the xmltodict library.
[EXTERNAL_DOWNLOADS]: The skill mentions external dependencies including the nmap binary (via apt or brew) and the xmltodict Python package.

network-scan-nmap