qinghu-ad-film

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 0.90). The skill instructs the agent to ask the user for an API token and pass it directly into a command-line argument (qhkit config set --token <密钥>), exposing the secret value in the LLM's context and output.

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

• Potentially malicious external URL detected (high risk: 0.70). The skill instructs the agent to download and install Node.js binaries and packages from nodejs.org and npmmirror.com during runtime setup if dependencies are missing, creating an unverifiable operational dependency.