cnki-advanced-search
Pass
Audited by Gen Agent Trust Hub on Jul 8, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill is designed for academic research automation, targeting a well-known academic database (CNKI).
- [COMMAND_EXECUTION]: The skill utilizes browser-based evaluation (
browser action=act kind=evaluate) to perform DOM manipulations. This is a standard and expected method for web automation tasks. - [EXTERNAL_DOWNLOADS]: The skill interacts with the legitimate CNKI domain (
kns.cnki.net). No unauthorized or suspicious external connections were identified. - [DATA_EXFILTRATION]: The skill retrieves research metadata (result counts, page indicators) and returns it to the agent context. There is no evidence of sensitive local file access or exfiltration to third-party servers.
Audit Metadata