k8s-autoscaling

Pass

Audited by Gen Agent Trust Hub on Nov 9, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection attacks because it ingests untrusted data from an external environment and has the capability to perform state-changing operations.
  • Ingestion points: The skill reads resource definitions, status updates, and cluster events using tools like kubectl_get, keda_scaledobject_get, and kubectl_describe (SKILL.md, KEDA-TRIGGERS.md).
  • Boundary markers: There are no explicit instructions or delimiters used to help the agent distinguish between its operational instructions and the data retrieved from the Kubernetes cluster.
  • Capability inventory: The skill has the capability to modify the cluster environment via kubectl_apply (SKILL.md).
  • Sanitization: The skill does not implement sanitization or validation logic for the content of the Kubernetes objects it processes.
Audit Metadata
Risk Level
SAFE
Analyzed
Nov 9, 2026, 06:52 PM