triz-functional-search
Pass
Audited by Gen Agent Trust Hub on Aug 27, 2026
Risk Level: SAFENO_CODE
Full Analysis
- [SAFE]: The skill contains only instructional text and markdown metadata. No executable code, scripts, or dangerous command patterns are present.
- [SAFE]: No evidence of prompt injection, data exfiltration, or obfuscation was found in the instructions.
- [SAFE]: The skill references the use of Patsnap/Zhihuiya MCP data, which is consistent with the author's identity and represents standard platform data access for the intended research purpose.
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to process user-supplied technical problems. While this constitutes an input surface, the skill lacks any high-privilege capabilities or dangerous tools that could be exploited through this channel.
Audit Metadata