kubectl-debugging
Pass
Audited by Gen Agent Trust Hub on Feb 27, 2026
Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADS
Full Analysis
- [COMMAND_EXECUTION]: The skill permits the execution of kubectl and stern commands, which are the primary tools for the intended Kubernetes debugging tasks. This includes high-privilege operations such as node debugging and the use of sysadmin profiles, which are consistent with the skill's primary purpose.
- [EXTERNAL_DOWNLOADS]: The skill references standard, well-known container images such as busybox, alpine, and nicolaka/netshoot for use in troubleshooting pods.
- [PROMPT_INJECTION]: The skill exhibits an indirect prompt injection surface as it processes cluster data. 1. Ingestion points: Resource names, metadata, and container logs from kubectl and stern (SKILL.md, REFERENCE.md). 2. Boundary markers: None. 3. Capability inventory: Bash(kubectl *), Bash(stern *), WebFetch, Write. 4. Sanitization: None.
- [SAFE]: No security issues were identified; the skill includes critical safety instructions for managing Kubernetes contexts to prevent operations on unintended clusters.
Audit Metadata