The Agent Skills Directory

[COMMAND_EXECUTION]: The skill instructs the agent to execute shell commands to inspect local network configurations (e.g., ip addr, arp -a, net view) and perform active scanning with third-party tools like nmap and fscan.
[EXTERNAL_DOWNLOADS]: The documentation references external security tools including fscan, httpx, and nmap. However, the skill does not implement automated downloading or installation of these tools, instead referring to a separate tool-delivery process.
[PROMPT_INJECTION]: The skill contains a surface for indirect prompt injection as it processes data from untrusted network environments through scanner results and local configuration files.
Ingestion points: Scanner outputs (fscan, nmap) and network configuration files (/etc/hosts, /etc/resolv.conf) are processed by the agent.
Boundary markers: Absent in instructions.
Capability inventory: Extensive shell command execution across multiple files.
Sanitization: No explicit sanitization or validation of tool output is described.
This risk is evaluated as safe within the context of the skill's primary function of network reconnaissance.

internal-recon