skills/clawlink-hq/skills/notion/Gen Agent Trust Hub

notion

Pass

Audited by Gen Agent Trust Hub on Jun 28, 2026

Risk Level: SAFE
Full Analysis
  • [COMMAND_EXECUTION]: The skill uses shell commands to invoke @useclawlink/cli, which is the vendor's tool for managing service integrations.
  • [EXTERNAL_DOWNLOADS]: The skill utilizes npx to fetch the @useclawlink/cli package from the official NPM registry. This is a standard and expected delivery method for this vendor's functionality.
  • [CREDENTIALS_UNSAFE]: The skill documents that credentials obtained via browser login are stored at ~/.clawlink/credentials.json. This is standard local storage behavior for CLI applications, equivalent to other developer tools like the AWS or GitHub CLIs.
  • [PROMPT_INJECTION]: The instructions include a safety directive to "confirm with the user before any write," which acts as a security best practice to prevent the agent from performing unintended modifications to the user's Notion workspace.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 28, 2026, 02:43 PM
Security Audit — agent-trust-hub — notion