notion
Pass
Audited by Gen Agent Trust Hub on Jul 13, 2026
Risk Level: SAFE
Full Analysis
- [PROMPT_INJECTION]: The skill establishes an indirect prompt injection surface by providing mechanisms to read content from external Notion pages and databases. Content authored by third parties in Notion could potentially contain instructions designed to manipulate the agent's logic.
- Ingestion points: Reading page blocks via
GET /v1/blocks/{page_id}/childrenas described in the API Basics and Common Operations sections. - Boundary markers: The instructions do not define specific delimiters or warnings to ignore instructions embedded within retrieved Notion data.
- Capability inventory: The skill's functionality is limited to interacting with the Notion API using
curl; it does not include local script execution or file-system modification capabilities based on the retrieved content. - Sanitization: There is no mention of filtering or sanitizing content retrieved from the API before it is processed by the agent.
Audit Metadata