k8s-image-audit

Pass

Audited by Gen Agent Trust Hub on Aug 13, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill uses shell commands including kubectl, helm, and jq to inspect Kubernetes resources, pull policies, and volume status. These operations are core to the skill's functionality for auditing deployments.
  • [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it ingests and processes data from external systems (Kubernetes cluster metadata and Helm releases) and local files (.claude/logs/docker-builds.jsonl).
  • Ingestion points: Data retrieved from kubectl get pods, helm list, helm get values, and the local .claude/logs/docker-builds.jsonl file.
  • Boundary markers: The skill does not provide explicit instructions to the agent to treat ingested data as untrusted or to use specific delimiters.
  • Capability inventory: The agent has the ability to execute shell commands (kubectl, helm, jq) which could be influenced by malicious data found in the audited resources.
  • Sanitization: There is no evidence of sanitization or validation of the data retrieved from the cluster before it is processed by the agent.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 13, 2026, 10:14 AM
Security Audit — agent-trust-hub — k8s-image-audit