notion
Pass
Audited by Gen Agent Trust Hub on Jul 27, 2026
Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSDATA_EXFILTRATIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill uses the
curlutility to perform HTTP requests to the Notion API. - [EXTERNAL_DOWNLOADS]: The skill communicates with
api.notion.com, which is the official endpoint for the well-known Notion service. - [DATA_EXFILTRATION]: The skill retrieves a Notion API key from
~/.config/notion/api_keyand transmits it toapi.notion.comvia an Authorization header for legitimate authentication. - [PROMPT_INJECTION]: The skill processes data from Notion pages and blocks, creating a surface for indirect prompt injection attacks.
- Ingestion points: Content is retrieved from external sources via
GET /v1/pages/{page_id}andGET /v1/blocks/{page_id}/childrenas documented in SKILL.md. - Boundary markers: No specific delimiters or safety instructions are provided to the agent to help it distinguish between data and instructions within the ingested Notion content.
- Capability inventory: The skill allows the agent to perform extensive operations including searching, reading, creating, and modifying Notion content using
curl. - Sanitization: The instructions do not describe any mechanisms for validating or sanitizing the content fetched from Notion before it is processed.
Audit Metadata