k8s-security-policies
Pass
Audited by Gen Agent Trust Hub on Feb 16, 2026
Risk Level: LOW
Full Analysis
- [Prompt Injection] (SAFE): The skill contains no instructions designed to bypass agent safety filters or override core instructions.
- [Data Exposure & Exfiltration] (SAFE): No hardcoded secrets, API keys, or network exfiltration patterns were found. The references to Kubernetes 'secrets' are restricted to template RBAC roles for educational and configuration purposes.
- [Unverifiable Dependencies & Remote Code Execution] (SAFE): The skill does not perform any external package installations or remote script executions. It relies on local references and standard Kubernetes manifests.
- [Privilege Escalation] (SAFE): Although the skill provides templates for high-privilege Kubernetes roles (e.g., secret-reader ClusterRole), these are contextually appropriate for a security configuration skill and do not attempt to escalate the agent's or the user's host-level permissions.
- [Obfuscation] (SAFE): No Base64 encoding, zero-width characters, or other techniques for hiding malicious content were identified.
- [Indirect Prompt Injection] (LOW): As a template-providing skill, it does not ingest untrusted data from external URLs or APIs, significantly limiting the surface area for indirect injection.
Audit Metadata