The Agent Skills Directory

[COMMAND_EXECUTION]: The skill provides instructions to install and execute the 'pygount' command-line tool to perform repository analysis.
Evidence: Commands such as python -m pip install pygount and pygount --format=summary are detailed in the SKILL.md file.
[EXTERNAL_DOWNLOADS]: The skill initiates the download and installation of a Python package from a public registry.
Evidence: The prerequisites section guides the agent to use pip to install pygount within a virtual environment.
[INDIRECT_PROMPT_INJECTION]: The skill creates an attack surface by ingesting and processing content from untrusted external repositories.
Ingestion points: The skill uses pygount to scan and read all files within a user-specified repository path.
Boundary markers: Absent; there are no specific markers or instructions to help the agent distinguish between the tool's metric output and potentially malicious instructions embedded in the scanned files.
Capability inventory: The agent has the capability to run shell commands (pygount, sort, pip) and read the local filesystem.
Sanitization: Absent; the tool output is processed and returned without explicit filtering or sanitization of the file content being scanned.

codebase-inspection