The Agent Skills Directory

[COMMAND_EXECUTION]: The skill executes local git commands (e.g., git rev-parse, git status) via Python's subprocess module to collect repository metadata. These calls are implemented using list-based arguments without spawning a shell, which is a secure practice that avoids command injection vulnerabilities.
[DATA_EXPOSURE]: The skill includes a proactive security layer in scripts/build_knowledge.py designed to detect and exclude sensitive information. It uses regex patterns to identify potential API keys, private keys, and authentication tokens, ensuring they are not included in the generated knowledge artifacts.
[SAFE]: The skill's primary functionality—repository intelligence and task resolution—is performed entirely through local file analysis (AST parsing for Python and regex for other languages). It contains no network exfiltration logic, remote code execution patterns, or obfuscated content.

build-codebase-knowledge