omh-morning-brief
Pass
Audited by Gen Agent Trust Hub on Sep 25, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill is primarily instructional and does not contain executable scripts, external binary downloads, or malicious command execution.
- [SAFE]: Explicit safety guardrails are implemented, requiring that email and calendar access be restricted to 'read and draft-only' scopes, ensuring that the agent cannot send emails autonomously.
- [SAFE]: The instructions mandate the use of secure entry or user-side OAuth setup, strictly forbidding the requesting or sharing of secrets or credentials within the chat interface.
- [SAFE]: Configuration changes are limited to a 'diff-approved apply' model, where users must review and explicitly approve changes to local configuration or
.envfiles with redacted placeholders.
Audit Metadata