humanizer
Pass
Audited by Gen Agent Trust Hub on Mar 19, 2026
Risk Level: SAFEPROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [PROMPT_INJECTION]: The skill processes arbitrary user-provided text, creating a surface for indirect prompt injection. \n
- Ingestion points: User-provided text passed for humanization in
SKILL.md. \n - Boundary markers: Absent. The instructions do not define delimiters to separate input data from the skill's operational prompts. \n
- Capability inventory:
Read,Write,Edit,Grep, andGlobpermissions enable modification of the user's file system. \n - Sanitization: Absent. No filtering or input validation is performed on the ingested text. \n- [COMMAND_EXECUTION]: The documentation in
README.mdandWARP.mdprovides shell commands for manual installation, includinggit clonefrom a non-whitelisted third-party repository (github.com/blader/humanizer.git).
Audit Metadata