yuque-personal-smart-summary
Pass
Audited by Gen Agent Trust Hub on Sep 16, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes external document content that could contain malicious instructions designed to influence the agent's behavior during the summarization process.
- Ingestion points: Document content retrieved from the
yuque_get_doctool as described in Step 3 and Step 6 of the workflow inSKILL.md. - Boundary markers: Absent. The skill instructions do not provide delimiters or specific prompts to the agent to ignore instructions embedded within the document text.
- Capability inventory: The skill utilizes
yuque_list_repos,yuque_get_repo_toc,yuque_get_doc, andyuque_searchto access and read private user data. - Sanitization: Absent. There is no evidence of content filtering, escaping, or validation of the text retrieved from Yuque before it is processed by the model.
Audit Metadata