qiqi-cli
Pass
Audited by Gen Agent Trust Hub on Sep 21, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill uses a localized command-line utility for all operations, following structured data patterns (JSON) and explicit metadata discovery to prevent command injection or data misinterpretation.
- [SAFE]: Authentication and credential safety are prioritized, with explicit instructions forbidding the agent from requesting, storing, or outputting user credentials.
- [SAFE]: The instructions mandate human-in-the-loop confirmation for all high-risk operations, such as record deletion or executing business actions with warnings.
- [SAFE]: Data processing is restricted to verified fields and objects discovered through the tool's own discovery commands, reducing the risk of processing malicious or unintended data structures.
Audit Metadata