notion

Pass

Audited by Gen Agent Trust Hub on Mar 9, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill provides illustrative examples of interacting with the official Notion API at api.notion.com. All documented methods are standard and align with official API usage.
  • [DATA_EXFILTRATION]: The setup instructions guide users to store their integration key in a local configuration file at ~/.config/notion/api_key. While this involves sensitive credentials, it is a routine pattern for command-line tools and is required for the intended functionality of the skill.
  • [PROMPT_INJECTION]: The skill facilitates the ingestion of external data from Notion pages and databases, which presents a surface for indirect prompt injection.
  • Ingestion points: Data is retrieved through page and block retrieval endpoints as documented in SKILL.md.
  • Boundary markers: No delimiters or instructions to ignore embedded content are specified in the documentation.
  • Capability inventory: The skill allows the agent to search, read, create, and update Notion content using the API.
  • Sanitization: There is no mention of sanitizing or validating the content retrieved from Notion before it is processed.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 9, 2026, 10:15 PM