The Agent Skills Directory

[COMMAND_EXECUTION]: The skill provides shell command templates using curl, grep, and jq intended for execution against a user-specified $TARGET variable to perform network reconnaissance.
[EXTERNAL_DOWNLOADS]: The skill performs network requests via curl to arbitrary external targets to retrieve headers, HTML content, and JSON data for analysis.
[DATA_EXFILTRATION]: The skill provides instructions for discovering and retrieving potentially sensitive data from target systems, such as WooCommerce product/order/customer JSON endpoints and Untappd API keys embedded in HTML.
[PROMPT_INJECTION]: The skill has an indirect prompt injection surface due to the processing of untrusted external data. * Ingestion points: The $TARGET variable in shell commands across the Step-by-Step section of SKILL.md. * Boundary markers: Absent. * Capability inventory: Shell execution capabilities using curl, grep, and jq documented in SKILL.md. * Sanitization: Absent; the skill does not include logic to sanitize or escape the $TARGET input before interpolation into shell commands.

recon-breweries