The Agent Skills Directory

[COMMAND_EXECUTION]: The skill executes a Node.js script at .agents/skills/platform/skill-lab.mjs. This is a local platform utility used for rule cataloging and does not involve remote code or arbitrary user input in the command line.
[INDIRECT_PROMPT_INJECTION]: The skill has a surface for indirect prompt injection because it reads and processes third-party skill files. * Ingestion points: Reads all files in the directory provided as skills-directory input. * Boundary markers: No explicit delimiters or instructions to ignore embedded commands are present in the prompt. * Capability inventory: The agent is instructed to run a specific node script (skill-lab.mjs) on the data. * Sanitization: No explicit sanitization or filtering of the content within the skill files is mentioned.

rule-cataloger