Trust Assessment
kubectl-skill received a trust score of 65/100, placing it in the Caution category. This skill has some security considerations that users should review before deployment.
SkillShield's automated analysis identified 2 findings: 1 critical, 1 high, 0 medium, and 0 low severity. Key findings include Potential Data Exfiltration via kubectl logs, Arbitrary Command Execution in Pods via kubectl exec.
The analysis covered 4 layers: Manifest Analysis, Static Code Analysis, Dependency Graph, LLM Behavioral Safety. The LLM Behavioral Safety layer scored lowest at 55/100, indicating areas for improvement.
Last analyzed on February 13, 2026 (commit 13146e6a). SkillShield performs automated 4-layer security analysis on AI skills and MCP servers.
Layer Breakdown
Behavioral Risk Signals
Security Findings2
| Severity | Finding | Layer | Location | |
|---|---|---|---|---|
| CRITICAL | Arbitrary Command Execution in Pods via kubectl exec The skill explicitly highlights `kubectl exec` as an "Essential Command" in `SKILL.md` and as a "Debug Tip" in `kubectl-pod-debug.sh` (`kubectl exec -it POD_NAME -- /bin/bash`). This command allows an AI agent to execute arbitrary commands inside any container within a pod, effectively granting remote code execution capabilities within the Kubernetes cluster. If an agent is compromised or misinterprets instructions, it could use this capability to perform malicious actions, install malware, exfiltrate data, or gain further access to the cluster. This represents a critical security risk due to the high level of control it provides. Implement stringent guardrails and explicit user consent mechanisms before allowing an agent to execute `kubectl exec`. Limit the scope of commands that can be executed via `exec` if possible. Consider using more constrained debugging tools or requiring human approval for interactive shell access. Ensure the agent's execution environment and permissions are minimized. | LLM | SKILL.md:59 | |
| HIGH | Potential Data Exfiltration via kubectl logs The `kubectl-pod-debug.sh` script explicitly uses `kubectl logs` with `--all-containers=true` to retrieve logs from all containers within a specified pod. Application logs often contain highly sensitive information such as PII, secrets, API keys, internal system states, and debugging data. An AI agent executing this script could easily read and exfiltrate this sensitive information from the Kubernetes cluster, leading to a significant data breach. Implement strict access controls and data handling policies for log output. Agents should be explicitly instructed and constrained on what log data they can access, process, and transmit. Consider redacting sensitive patterns from logs before they are exposed to the agent, or requiring explicit user confirmation for log access. Limit the scope of `kubectl logs` to specific containers or timeframes if possible. | LLM | scripts/kubectl-pod-debug.sh:26 |
Scan History
Embed Code
[](https://skillshield.io/report/abc47fbad26c413c)
Powered by SkillShield