The Agent Skills Directory

[SAFE]: The skill performs localized analysis and generation of markdown documentation. It does not perform network operations, access sensitive system files, or attempt to persist across sessions.
[DATA_EXPOSURE]: The validator.py script includes regular expression patterns designed to detect hardcoded secrets (such as API keys and passwords) within a user's CLAUDE.md file. This is a protective feature for the user and does not involve any actual secrets or sensitive data exposure within the skill itself.
[INDIRECT_PROMPT_INJECTION]: The skill possesses an ingestion surface as it processes user-provided CLAUDE.md content. However, the skill's capabilities are strictly limited to text analysis and generation. It lacks dangerous capabilities such as network access, arbitrary shell execution, or file-writing outside of its specific documentation purpose, which mitigates the risk of injection-based attacks.

claude-md-enhancer