humaniser
Pass
Audited by Gen Agent Trust Hub on Apr 16, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill is a focused text-transformation tool. It does not perform network communication, handle credentials, or access sensitive files.\n- [SAFE]: No external code is downloaded or executed. The skill uses a local reference catalog and standard instruction-following for its operations.\n- [PROMPT_INJECTION]: Indirect Prompt Injection Surface. The skill processes untrusted text provided by users for humanization and possesses file-writing capabilities (Write, Edit).\n
- Ingestion points: Processes arbitrary text provided by the user for rewriting as defined in SKILL.md.\n
- Boundary markers: No clear delimiters or warnings are used to isolate user data from the instructions.\n
- Capability inventory: The agent has access to Write and Edit tools as listed in the SKILL.md frontmatter.\n
- Sanitization: No input validation or content filtering is performed on the user text.
Audit Metadata