The Agent Skills Directory

[COMMAND_EXECUTION] (SAFE): The skill executes the cloc command locally to analyze the codebase. This is the intended primary function and is restricted to the current working directory without elevated privileges.
[PROMPT_INJECTION] (LOW): The skill possesses a surface for indirect prompt injection as it processes data from local files. 1. Ingestion points: Current directory files read by cloc. 2. Boundary markers: Absent in the output processing instructions. 3. Capability inventory: cloc execution and data interpretation. 4. Sanitization: Absent. The risk is considered low because cloc produces statistical summaries rather than executing file content.
[EXTERNAL_DOWNLOADS] (SAFE): The skill provides instructions for the user to install the 'cloc' utility manually if it is missing, rather than attempting to download or install software automatically.

analyze-size