digitalocean

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 0.90). The skill explicitly lists sensitive items in input/handoff (DO API token, kubeconfig, database connection string, Spaces keys) and requires producing HCL/CLI/YAML artifacts, which implies the LLM may be given and expected to embed secret values verbatim in outputs.