avoid-ai-writing
Pass
Audited by Gen Agent Trust Hub on Jun 14, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill's instructions and metadata do not contain any malicious patterns, such as persistence mechanisms, privilege escalation, or unauthorized access to sensitive system information.
- [EXTERNAL_DOWNLOADS]: The skill's documentation and changelog reference an external public GitHub repository (conorbronsdon/avoid-ai-writing) for upstream updates and version tracking. This reference is used for project maintenance and is categorized as a safe source.
- [PROMPT_INJECTION]: The skill processes untrusted user-supplied text during its audit and rewrite operations, creating an indirect prompt injection surface.
- Ingestion point: User-provided text or specified file content processed via the
rewrite,detect, andeditmodes defined inSKILL.md. - Boundary markers: The instructions do not define explicit delimiters or warnings to isolate processed text from agent instructions.
- Capability inventory: The skill utilizes the platform's native
Edittool to perform in-place file modifications. - Sanitization: No validation or sanitization of the input text is performed before it is integrated into the prompt context.
Audit Metadata