yuque-personal-smart-search
Pass
Audited by Gen Agent Trust Hub on Sep 16, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes and summarizes external content retrieved from Yuque documents, creating a potential surface for indirect instructions.
- Ingestion points: Document content is fetched from the Yuque API in
SKILL.md(Step 4). - Boundary markers: The instructions do not define specific delimiters to isolate fetched content from the rest of the prompt context.
- Capability inventory: The skill's capabilities are restricted to document search and retrieval; it lacks high-risk capabilities such as command execution, file system modifications, or arbitrary network access.
- Sanitization: There is no explicit sanitization of document content before it is provided to the agent for summarization.
Audit Metadata