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, andjqto 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.jsonlfile. - 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