The Agent Skills Directory

[COMMAND_EXECUTION]: The scripts/check_health_files.py script uses subprocess.run to call the gh CLI. This is used to query the GitHub API for community profile data, which is a standard administrative task for the skill's purpose. The command is constructed as a list, preventing shell injection.
[INDIRECT_PROMPT_INJECTION]: The skill reads existing repository files which may contain untrusted content.
Ingestion points: Files like CONTRIBUTING.md and CODE_OF_CONDUCT.md are read from the repository by the health check script.
Boundary markers: No explicit boundary markers or 'ignore' instructions are used when reading these files.
Capability inventory: The skill can write files to the local file system and execute the gh utility.
Sanitization: The script uses regular expression checks to identify placeholders and ensure content relevance, providing a layer of validation before the data is processed by the agent.

community-health