nssfc-proposal
Pass
Audited by Gen Agent Trust Hub on May 20, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill includes instructions for installation via a shell script hosted on the author's public GitHub repository (LeonChaoX/qinyan-academic-skills).\n- [COMMAND_EXECUTION]: To facilitate research, the agent is directed to execute a local bash utility (search.sh) within the skill's directory structure to query academic databases like Wanfang or Google Scholar.\n- [PROMPT_INJECTION]: The skill was evaluated for potential indirect injection through ingested research data. It mitigates this by instructing the agent to adhere to academic integrity standards and requiring the user to manually verify all facts and scientific claims.
Audit Metadata