split-claude-md
Pass
Audited by Gen Agent Trust Hub on Nov 8, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill's primary function is to manage and reorganize local project documentation and configuration files.
- [INDIRECT_PROMPT_INJECTION]: The skill ingests data from project files such as CLAUDE.md and .claude/rules/*.md (Step 1 and 2). While it lacks explicit boundary markers or sanitization, it mitigates risk by requiring a user-approved proposal (Step 4) before performing any file write operations. It has no capabilities for network access or code execution.
Audit Metadata