ai-vision

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 0.80). The prompt explicitly allows/encourages passing an API key via a --api-key flag or base-url/model flags (which would require embedding secrets into generated CLI commands or requests), even though env-var usage is mentioned, so there is a high risk the LLM would need to handle/output secret values verbatim.