The Agent Skills Directory

[COMMAND_EXECUTION]: The skill is designed to execute the fscan utility to perform internal network reconnaissance, service identification, and active exploitation tasks. This includes functionalities such as port scanning, credential brute-forcing, and executing commands on remote targets via SSH or WMI.
[INDIRECT_PROMPT_INJECTION]: The skill ingests and interprets output from network scans, including host NetBIOS information, Web titles, and service banners. This creates an injection surface where a malicious internal host could provide crafted metadata to influence the agent's reasoning during result interpretation.
Ingestion points: Terminal output generated by fscan scan results (SKILL.md).
Boundary markers: None identified; the skill instructions do not provide delimiters or warnings to ignore embedded content in tool outputs.
Capability inventory: The skill possesses significant capabilities including high-concurrency network scanning, interaction with sensitive files (e.g., -rf for SSH key writing), and remote shell command execution.
Sanitization: No explicit sanitization, validation, or filtering of the external tool output is implemented in the skill's prompt logic.

fscan-scan