yuque-group-tech-design
Pass
Audited by Gen Agent Trust Hub on Sep 16, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill creates a surface for indirect prompt injection by ingesting external data and user input without proper isolation or sanitization.
- Ingestion points: The skill retrieves external data through the
yuque_searchtool and incorporates requirements provided directly by the user. - Boundary markers: The instructions do not define clear delimiters (such as XML tags, unique strings, or specific ignore-instructions) to separate external search results or user content from the internal design generation logic.
- Capability inventory: The skill possesses write capabilities through the
yuque_create_doctool, enabling it to save generated content to the team's repository. - Sanitization: No evidence of validation, filtering, or escaping is present for data retrieved from external sources before it is interpolated into the
references/template.mdfields.
Audit Metadata