coreweave-enterprise-rbac
Pass
Audited by Gen Agent Trust Hub on Sep 9, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill makes extensive use of the
kubectlCLI via theBashtool to perform administrative operations, including creating namespaces, resource quotas, and role bindings. - [INDIRECT_PROMPT_INJECTION]: The TypeScript examples in
SKILL.md(specifically theassignTeamNamespacefunction) interpolate theteamandgrouparguments directly into shell command strings forkubectl. - Ingestion points: Untrusted data enters the agent context through the
teamandgroupvariables in theassignTeamNamespacefunction. - Boundary markers: There are no boundary markers or instructions for the agent to validate or sanitize these inputs before execution.
- Capability inventory: The skill has the capability to execute arbitrary shell commands via the
Bash(kubectl:*)tool. - Sanitization: No sanitization or input validation logic is present in the provided snippets to prevent shell meta-character injection.
Audit Metadata