humanizer
Pass
Audited by Gen Agent Trust Hub on Nov 7, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill contains no executable code, scripts, or obfuscated content. It is composed entirely of markdown instructions and an MIT license file.
- [INDIRECT_PROMPT_INJECTION]: Ingestion point: The skill reads local files for voice calibration (SKILL.md). Boundary markers: Absent. Capability inventory: Read, Write, Edit, Grep, Glob, AskUserQuestion. Sanitization: Absent. The risk is assessed as safe because the skill is restricted to text manipulation and lacks shell or network tools.
- [EXTERNAL_DOWNLOADS]: The skill does not request network permissions and does not attempt to download external resources at runtime.
Audit Metadata