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 curl to 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
Risk Level
SAFE
Analyzed
Sep 8, 2026, 07:01 PM
Security Audit — agent-trust-hub — notion