runai-get-cluster-health-summary
Pass
Audited by Gen Agent Trust Hub on Nov 2, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill is designed with a read-only architecture. It explicitly forbids the agent from running any shell commands, including
kubectlor therunaiCLI, and strictly prohibits operations that modify the cluster environment (e.g., cordoning or draining nodes). - [INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted data from the Run:ai MCP tools, specifically workload status messages, reasons, and events. This creates a potential surface for indirect prompt injection. However, the skill provides specific instructions to mitigate this by directing the agent to treat tool output as untrusted and to never follow instructions found within that data. The risk is further minimized by the skill's limited read-only capability set.
Audit Metadata