dex-plan

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 1.00). The skill explicitly tells the agent to read the full markdown context (via dex show) and "copy the full section content" into dex create --description command arguments, which would cause any API keys, tokens, or passwords present in the document to be output and passed verbatim on the command line.