linkpix-seedream-5-lite

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 an API key/token and then use it directly in a CLI command (qhkit config set --token <密钥> --env prod), which involves handling secret credentials directly.

MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).

• Potentially malicious external URL detected (high risk: 0.70). The skill instructs downloading and installing Node.js from nodejs.org via curl during runtime setup, presenting an unverified external binary execution dependency.