yueyang-house

Pass

Audited by Gen Agent Trust Hub on Jun 21, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: Fetches and executes the xiaolu-house Node.js package using npx. This is the official CLI tool provided by the vendor for accessing their real estate services.
  • [COMMAND_EXECUTION]: Runs various subcommands of the xiaolu-house CLI to retrieve property data and manage settings. This includes commands for checking supported cities and configuring local parameters.
  • [SAFE]: Manages configuration data, including an encrypted API key, stored locally at ~/.xiaolu-house/config. This is a standard practice for CLI-based authentication and does not represent an unsafe exposure.
  • [PROMPT_INJECTION]: The skill processes property data and listing details retrieved from external sources through the CLI, which constitutes an indirect prompt injection surface.
  • Ingestion points: Property listings, transaction data, and school information returned by the xiaolu-house tool.
  • Boundary markers: Not explicitly defined; the agent is instructed to use natural language to summarize findings.
  • Capability inventory: Execution of npx -y xiaolu-house commands.
  • Sanitization: None explicitly defined for the output of the CLI tool.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 21, 2026, 05:47 PM
Security Audit — agent-trust-hub — yueyang-house