Humanizer
Pass
Audited by Gen Agent Trust Hub on Mar 5, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill is composed entirely of markdown instructions. No external scripts, binaries, or sensitive file accesses were identified.
- [PROMPT_INJECTION]: The skill possesses an indirect prompt injection surface as it is designed to process arbitrary user text. However, this is inherent to its text-editing purpose and is considered safe given the limited tool set.
- Ingestion points: Processes user-provided text for stylistic editing in SKILL.md.
- Boundary markers: No specific delimiters or 'ignore' instructions are used for input data.
- Capability inventory: Utilizes standard Read, Write, Edit, and AskUserQuestion tools.
- Sanitization: No input sanitization is present in the skill instructions.
Audit Metadata