meeting-intelligence

Pass

Audited by Gen Agent Trust Hub on Oct 6, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill operates by ingesting data from external sources, specifically Notion databases and Calendar integrations, to generate meeting agendas as described in SKILL.md. While this creates an inherent surface for indirect prompt injection, it is the primary intended functionality of the skill. Ingestion points: Notion Meeting, Context, and Attendee databases. Boundary markers: The skill does not explicitly define delimiters for external data. Capability inventory: The skill utilizes Notion API access for reading records and creating new agenda pages. Sanitization: No specific sanitization or validation of external content is mentioned before it is processed by the agent.
  • [SAFE]: The skill references official Notion developer documentation, which is a well-known service and categorized as a safe external reference.
Audit Metadata
Risk Level
SAFE
Analyzed
Oct 6, 2026, 05:28 PM