Skills
skills/terminalskills/skills/k8s-cost-optimizer/Gen Agent Trust Hub

k8s-cost-optimizer

Pass

Audited by Gen Agent Trust Hub on Apr 11, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill uses kubectl to perform cluster info checks, node resource monitoring, and pod metadata retrieval. These commands are necessary for the skill's functionality and restricted to read-only telemetry gathering in the instructions.
  • [PROMPT_INJECTION]: The skill processes pod and container metadata which originates from the Kubernetes API and could be controlled by an attacker (indirect prompt injection). Ingestion point: kubectl get pods in SKILL.md. Boundary markers: None. Capability inventory: kubectl in SKILL.md. Sanitization: Uses jq for structured JSON parsing, which mitigates simple command injection risks.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 11, 2026, 08:55 PM