image-upload

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 1.00). The skill explicitly instructs the agent to read the API key via echo $LABNOCTURNE_API_KEY or extract a returned api_key and then embed that secret verbatim into generated commands (the curl Authorization header), which causes the LLM to handle and output secret values directly.