skills/magnus919/agent-skills/notion/Gen Agent Trust Hub

notion

Pass

Audited by Gen Agent Trust Hub on Aug 5, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill facilitates communication with api.notion.com, a well-known cloud service. It correctly manages integration tokens via environment variables, avoiding hardcoded credentials.
  • [PROMPT_INJECTION]: Although the skill ingests external data from Notion pages and databases, it mitigates the risk of indirect prompt injection by summarizing output to IDs, titles, and URLs, and explicitly instructing the agent against dumping raw content blocks.
  • [COMMAND_EXECUTION]: The skill utilizes a local Python script (notion-cli) to interact with Notion. This script is implemented without external dependencies and uses standard Python practices for command execution, primarily in its test suite to verify CLI behavior.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 5, 2026, 09:20 PM
Security Audit — agent-trust-hub — notion