The Agent Skills Directory

[COMMAND_EXECUTION]: The skill uses several local shell commands (including curl, seq, shuf, grep, awk, and python3 -c) to automate network requests, generate brute-force payloads, and perform statistical timing analysis.
[DATA_EXFILTRATION]: The instructions facilitate sending large volumes of authentication attempts and custom headers (e.g., X-Forwarded-For rotation) to external target servers for the purpose of testing defensive controls.
[EXTERNAL_DOWNLOADS]: The skill references the use of external security binaries such as ffuf, hydra, and nuclei to perform high-throughput testing.
[PROMPT_INJECTION]:
Ingestion points: Network responses from the $TARGET server (HTTP status codes, response headers, and body content) are read into the agent's context during various phases.
Boundary markers: None present; the agent processes raw output from the curl and ffuf commands.
Capability inventory: The skill has access to shell execution (subprocess) for running network tools and local file manipulation in the /tmp/ directory.
Sanitization: The skill does not implement sanitization or validation of the content received from external targets before it is processed by the agent's logic.

hunt-brute-force