tongliao-house

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 1.00). The skill explicitly shows and requires executing CLI commands like npx -y xiaolu-house config --set-api-key <your-api-key> and states the agent will run all npx commands, which would force the model to accept and embed an API key as a command-line argument (verbatim secret) — an exfiltration risk.

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

• Potentially malicious external URL detected (high risk: 1.00). The skill mandates running "npx -y xiaolu-house" at runtime, which fetches and executes remote package code from the npm registry (e.g. https://registry.npmjs.org/xiaolu-house), so an external resource is executed and can control agent behavior.