zhang-yiming-perspective
Pass
Audited by Gen Agent Trust Hub on Apr 9, 2026
Risk Level: SAFE
Full Analysis
- [PROMPT_INJECTION]: The skill includes detailed persona instructions and specific handling for sensitive or political topics (recommending neutrality or silence). These instructions are designed for character consistency and do not attempt to bypass underlying safety filters or extract system prompts.
- [EXTERNAL_DOWNLOADS]: The instructions mandate the use of web search tools to gather real-time data for factual queries. This is a legitimate use of agentic tools for data grounding and does not involve downloading untrusted scripts or executables.
- [SAFE]: A thorough review of the skill and its research references found no evidence of code obfuscation, hardcoded credentials, data exfiltration, or persistence mechanisms. The skill operates within standard role-playing boundaries.
Audit Metadata