chinese-copyfix
Pass
Audited by Gen Agent Trust Hub on Oct 16, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill is composed entirely of markdown instructions for the AI model to follow. It contains no executable scripts, system commands, or external dependencies.
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted user-provided text for rewriting. 1. Ingestion points: User-provided text enters via instructions in SKILL.md. 2. Boundary markers: Absent. 3. Capability inventory: The skill contains no code or tools with file system, network, or subprocess capabilities. 4. Sanitization: Absent.
Audit Metadata