notion
Pass
Audited by Gen Agent Trust Hub on Sep 8, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill retrieves and processes arbitrary text and block content from the Notion API, which could potentially contain malicious instructions intended to influence the AI agent's behavior.
- Ingestion points: Data is ingested from the Notion API endpoints (api.notion.com) via search and block retrieval commands in
SKILL.md. - Boundary markers: No explicit delimiters or boundary markers are defined to separate external Notion content from the agent's system instructions.
- Capability inventory: The skill uses
curlto interact with the Notion API, providing capabilities to read, search, create, and update pages and databases. - Sanitization: The skill does not implement sanitization, filtering, or validation of the content retrieved from Notion before passing it to the agent.
Audit Metadata