The Agent Skills Directory

[SAFE]: The skill's analysis engine consists of Python scripts that use only the standard library for regex-based parsing of Go source files.
No external dependencies or third-party packages are requested or installed.
The scripts (cartographer.py, cartographer_omni.py, cartographer_ultimate.py) perform only local file read/write operations for analysis and reporting.
[SAFE]: No prompt injection or safety bypass instructions were detected in the documentation or system instructions.
The documentation explicitly focuses on empirical measurement to reduce LLM training bias during code review and architecture analysis.
[SAFE]: No evidence of data exfiltration or credential harvesting was identified.
The scripts lack network functionality (e.g., no curl, requests, or urllib calls).
No sensitive file paths (like .ssh or .env) are accessed, and no hardcoded secrets were found in the source code.
[SAFE]: No privilege escalation, persistence mechanisms, or obfuscation techniques are present in the skill's instructions or scripts.

codebase-analyzer