notion-knowledge-capture

Pass

Audited by Gen Agent Trust Hub on Jul 16, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill facilitates the transformation of conversation history into structured Notion pages (FAQs, decision logs, etc.). All operations are consistent with standard documentation workflows.
  • [EXTERNAL_DOWNLOADS]: The documentation provides instructions to connect the agent to the official Notion MCP endpoint (https://mcp.notion.com/mcp). This is a well-known service and the reference is handled neutrally.
  • [COMMAND_EXECUTION]: Includes setup instructions for the local agent environment, such as adding the MCP server and performing OAuth login. These are standard configuration steps required for the skill to function.
  • [SAFE]: The skill possesses a surface for indirect prompt injection as it ingests conversation data and can write to Notion. However, this is the primary intended use case, and there are no signs of malicious patterns or instructions designed to exploit this behavior.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 16, 2026, 04:33 PM
Security Audit — agent-trust-hub — notion-knowledge-capture