group-meeting-notes

Pass

Audited by Gen Agent Trust Hub on Oct 25, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted meeting content from users and interpolates it into document templates before saving to the Yuque platform.
  • Ingestion points: User-provided meeting transcripts or unstructured notes (Step 1, SKILL.md).
  • Boundary markers: No explicit delimiters or instructions to ignore embedded commands are included in the workflow.
  • Capability inventory: Uses yuque_create_doc to perform network-based write operations to the Yuque service.
  • Sanitization: Instructions prioritize preserving original wording and do not include content sanitization or escaping logic.
Audit Metadata
Risk Level
SAFE
Analyzed
Oct 25, 2026, 06:59 AM