notion-rate-limits
Pass
Audited by Gen Agent Trust Hub on Sep 12, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill instructions and examples establish an ingestion surface for untrusted data from the Notion API into the agent's operating context.\n
- Ingestion points: Data from external Notion databases and pages is retrieved using the
notion.databases.queryandnotion.pages.retrievemethods as shown inSKILL.mdandreferences/examples.md.\n - Boundary markers: The provided implementation examples do not include delimiters or instructions to treat the ingested data as untrusted, which could lead the agent to follow instructions embedded in Notion content.\n
- Capability inventory: The skill leverages write capabilities to the Notion API, including
notion.pages.create,notion.pages.update, andnotion.blocks.children.append, which could be abused if malicious data is processed.\n - Sanitization: The patterns lack input validation or sanitization routines for the data fetched from the external API.
Audit Metadata