openclaw-china-integration

Pass

Audited by Gen Agent Trust Hub on May 17, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSREMOTE_CODE_EXECUTIONCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill installs several Node.js packages from the @openclaw-china scope to provide connectivity with platforms like DingTalk, QQ, and WeChat.\n- [REMOTE_CODE_EXECUTION]: Recommends using npx @openclaw-china/setup for an interactive configuration and environment setup process.\n- [COMMAND_EXECUTION]: Includes instructions for running installation and setup commands within the terminal.\n- [PROMPT_INJECTION]: The skill implements a processing flow that takes messages from external platforms and passes them to the agent, creating an indirect prompt injection surface.\n
  • Ingestion points: Message event handlers in SKILL.md for incoming platform content.\n
  • Boundary markers: None are defined in the provided code snippets.\n
  • Capability inventory: Includes message sending, media downloading via downloadMedia, and proactive messaging.\n
  • Sanitization: No sanitization of incoming text content is demonstrated in the integration examples.
Audit Metadata
Risk Level
SAFE
Analyzed
May 17, 2026, 07:27 AM
Security Audit — agent-trust-hub — openclaw-china-integration