notion
Pass
Audited by Gen Agent Trust Hub on Apr 6, 2026
Risk Level: SAFE
Full Analysis
- [COMMAND_EXECUTION]: The skill uses shell commands to read API credentials from the local filesystem at
~/.config/notion/api_key. This is a standard practice for managing access tokens in development-oriented skills. - [PROMPT_INJECTION]: The skill ingests data from external Notion pages (e.g., retrieving block children), which constitutes an indirect prompt injection surface.
- Ingestion points: Data is retrieved from the Notion API via
GET /v1/blocks/{page_id}/children. - Boundary markers: None identified in the provided instructions.
- Capability inventory: The skill has network access via
curland the ability to read local configuration files. - Sanitization: No specific sanitization or filtering of the retrieved Notion content is described.
Audit Metadata