The Agent Skills Directory

[COMMAND_EXECUTION]: The skill implements various command-line tools such as curl, jq, ffuf, and nuclei within bash and Python scripts to automate security probing and vulnerability verification.- [EXTERNAL_DOWNLOADS]: The skill facilitates network communication with remote target servers to test for security misconfigurations, using standard libraries and utilities.- [PROMPT_INJECTION]: The skill processes data from external security tool outputs (e.g., httpx.jsonl), which represents an indirect prompt injection surface where untrusted input from scanned targets could potentially influence the agent's logic.

auth-bypass