outlook
Pass
Audited by Gen Agent Trust Hub on Jun 28, 2026
Risk Level: SAFE
Full Analysis
- [COMMAND_EXECUTION]: The skill instructions direct the agent to use the vendor's official CLI tool,
@useclawlink/cli, for authentication and to perform Outlook actions such as reading messages or creating events. - [EXTERNAL_DOWNLOADS]: The skill uses
npxto execute the@useclawlink/clipackage. This is a standard deployment mechanism for the vendor's tools provided via the NPM registry. - [CREDENTIALS_UNSAFE]: The documentation notes that authentication tokens are stored locally in the user's home directory at
~/.clawlink/credentials.json. This is a standard pattern for CLI-based authentication and does not involve hardcoded secrets in the skill itself. - [DATA_EXFILTRATION]: While the skill accesses sensitive email and calendar data, this behavior is aligned with the primary stated purpose of providing an Outlook integration via the vendor's infrastructure.
Audit Metadata