instantsearch

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 0.80). The skill prompt instructs the agent to ask the user for API keys and credentials, and then embed them directly into a curl command via environment variables (${API_KEY}, ${APP_ID}), which creates an exfiltration risk as the LLM processes and outputs commands containing secret values.