humanizer
Pass
Audited by Gen Agent Trust Hub on Sep 13, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill operates by ingesting untrusted text from users to identify and rewrite AI-generated patterns, which creates a potential vulnerability surface.
- Ingestion points: The skill reads untrusted data from user messages and local files via the
read_filetool as described inSKILL.md. - Boundary markers: The instructions lack specific guidance for using delimiters or boundary markers to isolate untrusted input from the agent's instructions.
- Capability inventory: The skill has the capability to modify the filesystem using
patchandwrite_filetools based on its processing of the untrusted input. - Sanitization: There is no documented logic for sanitizing or validating the contents of the processed text before it is presented to the user or written back to the disk.
Audit Metadata