notion-docs
Pass
Audited by Gen Agent Trust Hub on Sep 17, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill interacts with external Notion pages and databases, which creates a surface for indirect prompt injection if those sources contain malicious instructions.\n
- Ingestion points: Data is retrieved from Notion via MCP tools like search and fetch.\n
- Boundary markers: The skill does not define specific delimiters or instructions to ignore embedded commands within the ingested Notion content.\n
- Capability inventory: The agent can create or modify Notion pages and databases based on processed data.\n
- Sanitization: There is no explicit sanitization logic for data retrieved from Notion.\n- [EXTERNAL_DOWNLOADS]: The skill references official Notion resources for its operation.\n
- Evidence: Mentions the official hosted Notion MCP endpoint (https://mcp.notion.com/mcp) and the official local stdio server package (@notionhq/notion-mcp-server).
Audit Metadata