The Agent Skills Directory

[SAFE]: The skill performs its primary function by executing a script (anatomy.js) located within the trusted local plugin root. No external network requests or suspicious command patterns were identified.
[INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data from the local file system to generate a map.
Ingestion points: Reads file names, sizes, and metadata from the current working directory (${CWD}).
Boundary markers: No specific delimiters or safety instructions are used when presenting the generated map to the user.
Capability inventory: The skill uses the Bash and Read tools to execute the anatomy generator and read file data.
Sanitization: The instructions do not specify sanitization for file paths or metadata found in the environment.

cco-anatomy