lens
Pass
Audited by Gen Agent Trust Hub on Oct 11, 2026
Risk Level: SAFEDATA_EXFILTRATIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [DATA_EXFILTRATION]: The skill instructs the agent on how to manage sensitive Kubernetes configuration files.
- Evidence: The documentation refers to paths such as
~/.kube/config,~/.kube/prod-eks.yaml, and~/.k8slens/clusters.jsonwhich contain sensitive credentials. - [INDIRECT_PROMPT_INJECTION]: The skill provides instructions for viewing live pod logs and interactive shell output, which could contain malicious instructions from an attacker-controlled container.
- Ingestion points: Pod logs and container metrics described in
SKILL.md. - Boundary markers: Not present.
- Capability inventory: Interactive shell access and
kubectlexecution. - Sanitization: Not present.
Audit Metadata