coreweave-prod-checklist
Pass
Audited by Gen Agent Trust Hub on Sep 9, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill defines a structured checklist for DevOps tasks. The use of
kubectlvia theBashtool is restricted in the frontmatter and aligned with the primary purpose of managing inference services on CoreWeave infrastructure. - [INDIRECT_PROMPT_INJECTION]: The skill possesses a surface for indirect prompt injection as it processes live output from a Kubernetes cluster.
- Ingestion points: The skill retrieves pod status and rollout logs through
kubectl(found in SKILL.md). - Boundary markers: There are no specific delimiters or instructions to ignore embedded content in command outputs.
- Capability inventory: The skill uses
kubectlto apply manifests and perform rollbacks (found in SKILL.md). - Sanitization: There is no explicit sanitization or validation of the data returned by the Kubernetes API before it enters the agent's context.
Audit Metadata