notion-meeting-intelligence
Pass
Audited by Gen Agent Trust Hub on Sep 18, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill exhibits an attack surface for indirect prompt injection by ingesting untrusted data from an external source (Notion) and providing capabilities to write data back to the same environment.
- Ingestion points: The skill uses the
Notion:notion-fetchtool as described inSKILL.md(Step 1) and demonstrated inexamples/project-decision.md(Step 2) to pull content from external Notion pages into the agent's context. - Boundary markers: The instructions and provided templates in
reference/do not include clear delimiters or explicit instructions to the agent to ignore any embedded directives within the fetched content. - Capability inventory: The agent is granted capabilities to create and modify Notion content using
Notion:notion-create-pages,Notion:notion-update-page, andNotion:notion-create-commentas defined in theSKILL.mdworkflow. - Sanitization: There are no documented procedures for sanitizing or filtering the content retrieved from Notion before it is interpolated into the agent's prompts for generating meeting materials.
Audit Metadata