knowledge-connect
Pass
Audited by Gen Agent Trust Hub on Sep 16, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill ingests document content from a user's Yuque knowledge base to perform topic extraction and link analysis. This processing of potentially untrusted data constitutes a minor indirect prompt injection surface.
- Ingestion points: Document body content is retrieved via the
yuque_get_doctool in Step 2 of the workflow. - Boundary markers: The instructions do not define specific delimiters or instructions to prevent the agent from following commands that might be embedded within the documents being analyzed.
- Capability inventory: The skill has write permissions to the knowledge base via the
yuque_update_doctool, used to append "Related Notes" sections. - Sanitization: There is no evidence of content sanitization or instruction-filtering performed on the document text before analysis.
Audit Metadata