eks-resilience-checker

Pass

Audited by Gen Agent Trust Hub on Sep 21, 2026

Risk Level: SAFECOMMAND_EXECUTIONDYNAMIC_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill executes local shell commands using kubectl, aws, and jq to perform its assessment logic. These operations are essential for its primary purpose of evaluating infrastructure configuration and are correctly restricted to the local environment.\n- [DYNAMIC_EXECUTION]: In scripts/assess.sh, the skill generates a remediation-commands.sh file containing bash and kubectl commands to fix identified resilience issues. The instructions explicitly state that this file must be reviewed and executed manually by the user, and the agent is instructed not to execute it automatically.\n- [INDIRECT_PROMPT_INJECTION]: The skill ingests data from external sources (Kubernetes resource names, labels, and annotations) via kubectl get -o json to populate its reports. While this provides a surface for indirect prompt injection if the cluster data is attacker-controlled, the risk is inherent to the diagnostic use-case and the skill author (aws-samples) follows standard practices for structured data processing.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 21, 2026, 08:11 PM