eve-manifest-authoring
Pass
Audited by Gen Agent Trust Hub on Sep 16, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: No security vulnerabilities, malicious code, or suspicious patterns were detected in the skill instructions or examples.\n- [EXTERNAL_DOWNLOADS]: The manifest examples reference container images from well-known and trusted services, specifically Amazon ECR (public.ecr.aws) and GitHub Container Registry (ghcr.io). These images are used for platform-standard tasks like database migrations.\n- [CREDENTIALS_UNSAFE]: The skill encourages the use of secure secret management through ${secret.KEY} interpolation and the use of a dedicated .eve/dev-secrets.yaml for local development, which effectively prevents the hardcoding of sensitive credentials.\n- [COMMAND_EXECUTION]: The documentation describes the platform's native capability to discover and execute project-specific CLI tools. This is a standard infrastructure feature designed to provide agents with structured interfaces to services.
Audit Metadata