The Agent Skills Directory

[SAFE]: The skill functions as a documentation manager, using Python scripts to analyze project structures and generate markdown files based on predefined templates. It uses standard libraries and adheres to platform tool restrictions.
[SAFE]: The validator.py module includes a dedicated check for hardcoded credentials, scanning for API keys, passwords, and tokens within the analyzed project files. This provides a security-enhancing feature for the user's development environment.
[INDIRECT_PROMPT_INJECTION]: The skill exhibits an indirect prompt injection surface because it reads and processes untrusted local project files.
Ingestion points: Files are ingested via CLAUDEMDAnalyzer and BestPracticesValidator in analyzer.py and validator.py respectively.
Boundary markers: The skill does not explicitly wrap external content in delimiters when processing sections.
Capability inventory: The skill has access to file system operations (Read, Write, Edit) and limited shell commands (ls, find, git, wc).
Sanitization: While it lacks general prompt sanitization, it includes specific validation for security anti-patterns (hardcoded secrets). As this ingestion is core to the skill's primary purpose and involves local project data, the risk is assessed as safe.
[EXTERNAL_DOWNLOADS]: The skill documentation references official GitHub repositories and documentation from Anthropic, which are recognized as trusted organizations and well-known services.

claude-md-enhancer