meeting-intelligence

Pass

Audited by Gen Agent Trust Hub on Mar 5, 2026

Risk Level: SAFE
Full Analysis
  • [PROMPT_INJECTION]: The skill identifies a surface for indirect prompt injection because it ingests untrusted data from external sources (Notion pages and web research) and uses it to generate new documents.
  • Ingestion points: Notion pages (Step 2) and Web research results (Step 3).
  • Boundary markers: None present; the skill does not explicitly instruct the agent to ignore instructions embedded within the retrieved data.
  • Capability inventory: The skill has the capability to read Notion pages, perform web searches, and write new pages to Notion.
  • Sanitization: No specific sanitization or validation steps are defined for the external content before it is included in the meeting materials.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 5, 2026, 12:44 AM