The Agent Skills Directory

[SAFE]: The skill instructions and examples follow industry-standard software engineering practices for improving code maintainability. No malicious code, obfuscation, or data exfiltration attempts were detected.
[COMMAND_EXECUTION]: The skill relies on executing local command-line utilities such as radon, lizard, wily, and grep to analyze source code files. These operations are standard for development environments and are used exclusively for static analysis.
[INDIRECT_PROMPT_INJECTION]:
Ingestion points: The skill ingests and analyzes content from Python source code files (.py) within the repository.
Boundary markers: No specific delimiters or "ignore instructions" markers are defined for the ingested file content.
Capability inventory: The skill uses static analysis tools, file searching via grep, and provides refactoring suggestions. It does not possess network or broad file-write capabilities that could be leveraged for exfiltration.
Sanitization: The skill processes code for metric calculation; while it lacks explicit sanitization for potential embedded instructions in code comments, the risk is negligible given the read-only and local nature of the analysis tools.

py-complexity