humanizer
Pass
Audited by Gen Agent Trust Hub on Mar 3, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill is vulnerable to indirect prompt injection as it processes and modifies untrusted user content using file system tools without implementing security boundaries.
- Ingestion points: The skill acts on text provided for editing and humanization through tools like Read and Edit.
- Boundary markers: The instructions do not specify the use of delimiters to separate input text from core instructions.
- Capability inventory: The agent has access to file system operations including Read, Write, Edit, Grep, and Glob.
- Sanitization: There is no mechanism to sanitize input content for embedded instructions.
Audit Metadata