azure-kubernetes-automatic-readiness

Pass

Audited by Gen Agent Trust Hub on Sep 9, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [Indirect Prompt Injection Surface]: The skill evaluates user-provided Kubernetes manifests and live cluster data to identify compatibility issues. Processing untrusted external data is a security consideration, as it could potentially lead to indirect prompt injection. However, this is the primary purpose of the skill, and the risk is managed through guardrails such as read-only cluster access and mandatory user approval for local file modifications.\n
  • Ingestion points: Kubernetes manifest files (YAML) and live cluster configuration retrieved via the mcp_azure_mcp_aks tool.\n
  • Boundary markers: The skill logic relies on structured YAML parsing against a defined constraint spec.\n
  • Capability inventory: The skill uses the mcp_azure_mcp_aks tool and has file-writing capabilities for applying fixes.\n
  • Sanitization: The skill validates specific YAML fields but does not explicitly sanitize free-text fields in external data.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 9, 2026, 11:52 AM
Security Audit — agent-trust-hub — azure-kubernetes-automatic-readiness