humanizer
Pass
Audited by Gen Agent Trust Hub on Oct 16, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted input text and writing samples from users to identify and rewrite AI-isms. Because the skill is configured with tools to read, write, and edit files, malicious instructions embedded in the input text could potentially influence the agent's behavior.
- Ingestion points: The skill reads user-provided text inline or from a file path specified during 'Voice Calibration' in
SKILL.md. - Boundary markers: The instructions do not provide explicit delimiters or instructions to the agent to ignore potentially malicious commands within the text to be humanized.
- Capability inventory: The skill is authorized to use
Read,Write,Edit,Grep, andGlobtools across the file system. - Sanitization: There is no evidence of input validation or sanitization for the content processed by the skill.
Audit Metadata