writing-revision
Pass
Audited by Gen Agent Trust Hub on Apr 16, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill instructions and referenced resources are focused entirely on improving writing quality through systematic revision passes. The process is transparent and uses local file operations solely for tracking analysis findings.
- [PROMPT_INJECTION]: The skill possesses a surface for indirect prompt injection because it processes user-supplied text drafts. 1. Ingestion points: Draft text to be revised (SKILL.md). 2. Boundary markers: No explicit delimiters or instructions are used to isolate the draft text from agent instructions. 3. Capability inventory: The skill performs file system operations to create and read analysis reports (writer-pass1-clutter-analysis.md, etc.). 4. Sanitization: No sanitization of user-provided content is performed. This represents a standard surface for text-processing tools and does not indicate malicious intent.
Audit Metadata