humanizer
Pass
Audited by Gen Agent Trust Hub on Sep 21, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes user-supplied text to perform its humanizing rewrite, creating a potential surface for indirect injection.
- Ingestion points: Processes text provided by the user in the 'Workflow' and 'Inputs' sections of SKILL.md.
- Boundary markers: No explicit delimiters or boundary markers are defined to isolate user text from the skill's instructions.
- Capability inventory: The skill is instructed to write final drafts back to the local file system within the 'content/' directory.
- Sanitization: The skill lacks explicit sanitization steps for user-provided text before processing or writing.
- [SAFE]: The skill reads local files such as 'strategy/brand.md' and 'about/me.md' to align writing with a brand or personal voice. This access is appropriate for the skill's stated purpose and is restricted to the local workspace context.
Audit Metadata