reorganize
Pass
Audited by Gen Agent Trust Hub on Aug 15, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill ingests data from local project files that may contain untrusted content to generate its reorganization proposals.
- Ingestion points: Processes project-specific metadata and documentation (e.g., AGENTS.md, CONTRIBUTING, package.json) and source code hotspots as defined in the SKILL.md 'First Steps' section.
- Boundary markers: The instructions do not mandate the use of delimiters or instructions to ignore embedded commands when the agent reads external file content.
- Capability inventory: The agent has permissions to glob the filesystem, read file contents, and perform file system writes (moves and extractions) in the 'Apply' workflow stage.
- Sanitization: No explicit sanitization, filtering, or validation is performed on the content extracted from the project files.
Audit Metadata