project

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 1.00). The skill explicitly instructs the orchestrator to pass the full .fullstack-dev/config.json contents into agent prompts (e.g., "Pass: ... config contents" and "Config: <config.json contents>"), which would force the LLM to include any embedded secrets verbatim in its generated output.