The Agent Skills Directory

[COMMAND_EXECUTION]: The skill provides numerous shell commands for executing network reconnaissance tools including httpx, whatweb, curl, nuclei, and dig to identify infrastructure and software versions.
[EXTERNAL_DOWNLOADS]: Fetches a vulnerability repository from the official retirejs.github.io site to enable library version checking via the retire.js tool.
[EXTERNAL_DOWNLOADS]: Instructs the user to install the wafw00f tool via pip, facilitating third-party software installation from a public registry.
[INDIRECT_PROMPT_INJECTION]: The skill exposes a surface for indirect prompt injection by ingesting untrusted data from remote target servers. 1. Ingestion points: Data is collected from target hosts via curl, httpx, and whatweb (headers, cookies, and page content) as described in SKILL.md. 2. Boundary markers: The instructions do not define boundary markers to separate external data from agent instructions. 3. Capability inventory: The skill environment allows for shell command execution and network operations. 4. Sanitization: No sanitization of the retrieved host data is performed before it is processed by the agent.

fingerprinting