competition-k8s-control-plane
Pass
Audited by Gen Agent Trust Hub on Jul 17, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill is designed for security auditing and educational purposes in Kubernetes sandbox environments. It provides structured checklists and workflows for analyzing cluster permissions and potential misconfigurations.
- [PROMPT_INJECTION]: No direct prompt injection attempts were found. The skill has an indirect prompt injection surface as it processes external Kubernetes objects and secrets (Ingestion points: SKILL.md). While boundary markers and sanitization are not explicitly defined, the capabilities are consistent with the auditing use case.
- [DATA_EXFILTRATION]: While the instructions involve locating service account tokens and secrets within a cluster, no mechanisms or instructions for exfiltrating this data to external systems were found.
- [EXTERNAL_DOWNLOADS]: No external packages, scripts, or remote code patterns are downloaded or executed.
Audit Metadata