knock-migrate-to-knock
Pass
Audited by Gen Agent Trust Hub on Nov 4, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill is primarily focused on static discovery and documentation. It searches local codebase files (e.g.,
package.json,requirements.txt) to identify messaging SDKs and providers such as Braze, Courier, and SendGrid. - [SAFE]: The skill includes explicit security constraints in
SKILL.mdthat strictly forbid the agent from creating, updating, or deleting external Knock resources or running production imports without explicit user instructions. - [SAFE]: External communication is limited to referencing official documentation on the vendor's own domain (
docs.knock.app). - [SAFE]: The output is restricted to a local file (
knock-plan.md) at the repository root, ensuring that sensitive inventory data remains within the user's local environment unless shared manually. - [SAFE]: No evidence of obfuscation, malicious command execution, or unauthorized data exfiltration was found.
Audit Metadata