The Agent Skills Directory

[COMMAND_EXECUTION]: The skill utilizes nmap for network reconnaissance (host discovery, port scanning, and service detection) and curl for interacting with web services. These commands are executed via Bash and are essential to the skill's primary purpose.
[PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection as it processes unvalidated data from external network targets.
Ingestion points: Data is ingested via nmap scan results and curl HTTP response headers and bodies (SKILL.md).
Boundary markers: No boundary markers or delimiters are used to isolate tool output or warn the agent to ignore instructions embedded in the results.
Capability inventory: The agent has the capability to execute Bash commands (nmap, curl).
Sanitization: There is no evidence of output sanitization or filtering before the data is processed by the agent.

network-recon