chinese-write-checker
Pass
Audited by Gen Agent Trust Hub on Oct 28, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill's instructions focus exclusively on text analysis and quality reporting. No evidence of malicious behavior, credential harvesting, or unauthorized network communication was found.
- [INDIRECT_PROMPT_INJECTION]: The skill identifies a surface for indirect prompt injection by processing untrusted user articles for evaluation. 1. Ingestion points: User-provided text for article review in SKILL.md. 2. Boundary markers: Absent. 3. Capability inventory: No file system access, network operations, or subprocess execution capabilities across the skill. 4. Sanitization: Absent. The lack of dangerous capabilities mitigates the impact of potential injections.
Audit Metadata