azure-kubernetes-automatic-readiness

Pass

Audited by Gen Agent Trust Hub on Aug 18, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill processes untrusted Kubernetes manifests (YAML/JSON), Helm templates, and cluster workload data. This functionality introduces a surface for indirect prompt injection, where malicious instructions embedded in the data being analyzed could attempt to subvert the agent's instructions.
  • Ingestion points: Evaluates local manifest files, Helm charts, and cluster-level data retrieved through the mcp_azure_mcp_aks tool.
  • Boundary markers: The instructions lack explicit delimiters or safety instructions to distinguish between the agent's core logic and the potentially instructions-laden external data.
  • Capability inventory: The agent has the capacity to execute the mcp_azure_mcp_aks tool and generate diffs for file system changes.
  • Sanitization: The skill does not define methods for sanitizing or filtering instructions from the ingested manifests before processing.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 18, 2026, 12:22 PM
Security Audit — agent-trust-hub — azure-kubernetes-automatic-readiness