gpt-image-2

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 1.00). The skill instructs the agent to ask for the OPENAI_IMAGE_API_KEY and to embed it verbatim in shell commands/env assignments (e.g., OPENAI_IMAGE_API_KEY="sk-...") or to pass it inline to the script, which requires the LLM to handle and output secret values directly.