qu-ai-wei
Pass
Audited by Gen Agent Trust Hub on Sep 10, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill is a text-processing utility with no detected malicious patterns or dangerous command executions. The project structure is transparent and includes robust testing and validation scripts.
- [INDIRECT_PROMPT_INJECTION]: The skill processes user-supplied text, which is an inherent attack surface. However, the risk is mitigated as the skill lacks network, file-write, or code execution capabilities. It also includes explicit instructions to detect and halt on sensitive input like credentials, protecting the agent from accidental data leakage.
- [CREDENTIALS_UNSAFE]: The skill includes a 'door check' (门检) mechanism in its instructions specifically designed to identify and redact sensitive information like API keys, tokens, and private keys from the input before processing. This is a best-practice security feature.
Audit Metadata