ai-writing-detector
Pass
Audited by Gen Agent Trust Hub on Mar 17, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill's primary function is to provide stylistic analysis of Japanese text. It follows a structured approach to identify common AI linguistic patterns, such as specific vocabulary, repetitive sentence endings, and rigid structures, and offers constructive feedback for naturalizing the text.
- [SAFE]: No evidence of hardcoded credentials, unauthorized file access, or suspicious network operations was found. The instructions are focused entirely on the intended text-analysis utility.
- [SAFE]: The skill mentions using a 'Read tool' for analyzing files. This is a standard functional capability for document processing and is initiated by explicit user instruction to process a specific file path.
- [PROMPT_INJECTION]: The skill possesses a standard surface for indirect prompt injection as it processes untrusted user-provided text or file content for analysis.
- Ingestion points: Text inputs provided directly in conversation or file content accessed via the 'Read tool' (SKILL.md).
- Boundary markers: None explicitly defined for the input data in the instructions.
- Capability inventory: File reading capability via a 'Read tool' (SKILL.md).
- Sanitization: No specific sanitization or filtering of input content is mentioned.
Audit Metadata