notion

Pass

Audited by Gen Agent Trust Hub on Aug 19, 2026

Risk Level: SAFE
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill documentation enables the agent to read content from external Notion pages and databases, which can be manipulated by third parties.
  • Ingestion points: Data is ingested via the Notion API blocks and search endpoints described in SKILL.md.
  • Boundary markers: There are no instructions for the agent to use delimiters or ignore embedded instructions when processing content from Notion.
  • Capability inventory: The skill enables full read and write access to the user's connected Notion workspace via curl commands.
  • Sanitization: The retrieved content is processed without any suggested sanitization or validation of the text blocks.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 19, 2026, 07:46 PM
Security Audit — agent-trust-hub — notion