linkpix-jd-image

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 0.80). The skill instructs the agent to ask the user for an API key/token and then pass it directly into a command-line argument (qhkit config set --token <密钥>), which causes the secret to pass through the LLM context and output, presenting an exfiltration risk.