pod-management
Pass
Audited by Gen Agent Trust Hub on Nov 21, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill documents the use of powerful Kubernetes administrative commands. Examples include
kubectl execandkubectl debugfor interactive shell access to containers and cluster nodes,kubectl port-forwardwith the--address 0.0.0.0flag which exposes ports to the network, andkubectl cpfor file transfers. - [INDIRECT_PROMPT_INJECTION]: The skill facilitates the ingestion and processing of data from containerized environments. Ingestion points: The agent accesses container logs via
kubectl logs, reads file contents viakubectl cporkubectl exec cat, and monitors cluster events. Boundary markers: Absent; there are no specified delimiters to separate external data from agent instructions. Capability inventory: The skill allows modification of cluster resources viakubectl apply,create,delete, andrun. Sanitization: Absent; no instructions are provided for the agent to sanitize or validate the content retrieved from containers.
Audit Metadata