reclaude

Pass

Audited by Gen Agent Trust Hub on Mar 10, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill processes potentially untrusted data from CLAUDE.md files which creates a surface for indirect prompt injection.
  • Ingestion points: Reads CLAUDE.md, package.json, and Makefile from the project directory.
  • Boundary markers: The instructions lack explicit delimiters or 'ignore embedded instructions' warnings to isolate the content being refactored.
  • Capability inventory: The skill modifies the file system by reorganizing content into .claude/rules/ files.
  • Sanitization: No sanitization or input validation is performed on the ingested file content.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 10, 2026, 12:16 AM