humanizer
Pass
Audited by Gen Agent Trust Hub on Sep 18, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill involves processing arbitrary user-provided text to remove AI-generated patterns. This design introduces a surface where untrusted input is processed within the agent's context.
- Ingestion points: Untrusted text enters the agent's context via the
Readtool or direct input. - Boundary markers: The instructions do not specify the use of delimiters or warnings to ignore instructions embedded in the target text.
- Capability inventory: The skill utilizes
Read,Write,Edit,Grep, andGlobtools to perform its tasks. - Sanitization: There is no evidence of sanitization or validation of the input text before processing.
Audit Metadata