yuque-personal-daily-capture
Pass
Audited by Gen Agent Trust Hub on Sep 16, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes arbitrary user input and interpolates it into document titles and bodies within Yuque. This creates an attack surface where hidden instructions in the user's notes could potentially influence the behavior of the agent or downstream skills (e.g., the 'note-refine' skill mentioned in guidelines).
- [EXTERNAL_DOWNLOADS]: The skill relies on the
yuque-mcpserver. While documented as a legitimate vendor resource for Yuque, it involves remote API calls toapi.yuque.com. Per safety guidelines, this is documented as a vendor-specific download/integration but does not escalate the verdict on its own as it targets a well-known service provider.
Audit Metadata