yuque-group-meeting-notes
Pass
Audited by Gen Agent Trust Hub on Sep 16, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted raw meeting content and audio transcriptions provided by users.
- Ingestion points: Workflow Step 1 in
SKILL.mddescribes taking raw meeting info, audio transcripts, or pasted unstructured notes from the user as primary input. - Boundary markers: Absent. The instructions do not include specific delimiters or warnings to the agent to ignore instructions embedded within the meeting data.
- Capability inventory: The skill utilizes the
yuque_create_doctool to perform remote write operations to create documents in Yuque repositories. - Sanitization: Absent. The skill is explicitly instructed to preserve the user's original wording for decisions and action items, which provides a path for untrusted content to be included in the final archived document without filtering.
Audit Metadata