k8s-manifest-generator

Pass

Audited by Gen Agent Trust Hub on Feb 28, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill presents an indirect prompt injection risk by interpolating untrusted user data into generated Kubernetes YAML manifests.\n
  • Ingestion points: User requirements for workload configuration (e.g., app names, images, ports, and environment variables) are gathered in resources/implementation-playbook.md.\n
  • Boundary markers: No explicit delimiters or safety instructions are provided to the agent to prevent the execution of embedded instructions within the user-supplied data.\n
  • Capability inventory: The generated manifests (Deployments, ConfigMaps, Secrets) can define executable commands, lifecycle hooks, and sensitive configuration files, providing a substantial attack surface if the input is manipulated.\n
  • Sanitization: The implementation playbook and templates do not specify validation or sanitization steps to ensure that user inputs do not inject malicious YAML or script content.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 28, 2026, 05:10 PM