tianjin-house

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 0.90). The skill instructs the agent to execute CLI commands that include an API key flag (npx -y xiaolu-house config --set-api-key ) and states the agent will run all npx commands for the user, which can force the agent to handle or emit the API key verbatim as a command argument (high exfiltration risk).

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

• Potentially malicious external URL detected (high risk: 0.90). The skill explicitly requires running "npx -y xiaolu-house" at runtime, which downloads and executes the remote npm package (e.g. https://www.npmjs.com/package/xiaolu-house), so it relies on fetched external code that will be executed.