cnki-parse-results
Pass
Audited by Gen Agent Trust Hub on Mar 3, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill's primary function is to parse academic metadata (titles, authors, journals) from the CNKI (kns.cnki.net) search results page. No malicious behavior was detected.
- [COMMAND_EXECUTION]: The skill utilizes browser devtools to execute a static JavaScript block for data extraction. The script logic is hardcoded within the skill and does not dynamically generate code based on untrusted external input.
- [DATA_EXFILTRATION]: No evidence of unauthorized data transmission or credential harvesting was found. The extracted data is used solely for presentation to the user.
- [PROMPT_INJECTION]: The skill contains no instructions aimed at overriding agent safety guidelines or extracting system prompts.
Audit Metadata