humanize
Pass
Audited by Gen Agent Trust Hub on Oct 1, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes external text provided by the user to perform rewriting tasks, which creates a potential surface for indirect prompt injection.
- Ingestion points: The skill defines prompts in
SKILL.md(Quick Start) where user text is directly interpolated. - Boundary markers: The provided examples do not use clear delimiters (like triple backticks) to separate instructions from user-provided content.
- Capability inventory: The skill's functionality is limited to text editing; it lacks capabilities for network access, file system modifications, or shell execution.
- Sanitization: There is no logic to sanitize or filter potential instructions embedded within the text to be humanized.
- [SAFE]: The skill references writing guidelines from Wikipedia, an established well-known service.
- Evidence: A link to the 'Wikipedia:Signs of AI writing' page is included in the reference section of
SKILL.md.
Audit Metadata