rancher-cluster-inspection
Pass
Audited by Gen Agent Trust Hub on Feb 28, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill serves as a high-level orchestration template. It identifies and organizes inspection tasks without executing shell commands or scripts directly.
- [PROMPT_INJECTION]: The skill interpolates user-controlled variables (cluster names, namespaces) into sub-agent prompts. While this presents a potential surface for indirect prompt injection, it is the intended functionality for identifying target resources. The risk is minimized by the constrained scope of the inspection tasks and the use of specialized sub-agents.
- [DATA_EXFILTRATION]: No unauthorized data access or external transmission of cluster information was detected in the skill logic. The orchestration focuses on internal health metrics and reporting.
Audit Metadata