cc-devops-skills
Pass
Audited by Gen Agent Trust Hub on Sep 8, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill consists of operational guidelines, checklists, and templates for DevOps and Site Reliability Engineering workflows. It does not include any malicious scripts, persistence mechanisms, or unauthorized data exfiltration patterns. The skill explicitly advocates for security best practices, such as treating secrets as toxic data and avoiding their persistence in code or logs.
- [COMMAND_EXECUTION]: The skill provides standardized shell commands for Kubernetes diagnostics (e.g.,
kubectl get pods,kubectl logs,kubectl describe). These commands are intended for read-only troubleshooting and are consistent with the skill's primary purpose. No automated remote code execution or unauthorized shell access was detected. - [INDIRECT_PROMPT_INJECTION]: The skill is designed to analyze and review external artifacts, creating a potential surface for processing untrusted data.
- Ingestion points: The skill ingests user-provided infrastructure-as-code (IaC) files, Kubernetes manifests, and CI/CD configurations for review.
- Boundary markers: No explicit boundary markers or "ignore embedded instructions" delimiters are defined for the data processed during reviews.
- Capability inventory: The agent is empowered to execute diagnostic commands and generate configuration files based on the reviewed data.
- Sanitization: The skill mitigates risks by providing mandatory security checklists (e.g., the Kubernetes Readiness Checklist and Terraform IaC Checks) that focus on enforcing least privilege, dropping container capabilities, and ensuring secrets are managed through platform-native stores rather than files.
Audit Metadata