tongliao-house

Pass

Audited by Gen Agent Trust Hub on Jun 18, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill uses npx to download and execute the xiaolu-house package from the npm registry. This is a standard method for accessing Node-based CLI tools.
  • [COMMAND_EXECUTION]: The skill interacts with the user by executing xiaolu-house shell commands. This includes querying property listings and displaying configuration data.
  • [PROMPT_INJECTION]: The skill handles property listings and descriptions from an external service, which creates a potential surface for indirect prompt injection.
  • Ingestion points: Real estate listings and market data retrieved via the CLI (SKILL.md).
  • Boundary markers: None are specified to separate external data from agent instructions.
  • Capability inventory: Shell command execution using npx (SKILL.md).
  • Sanitization: The instructions do not specify any validation or sanitization for the data retrieved from the platform.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 18, 2026, 04:49 AM
Security Audit — agent-trust-hub — tongliao-house