openclaw-wechat-integration
Pass
Audited by Gen Agent Trust Hub on Jun 13, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill guides the user to install the
@canghe/openclaw-wechatplugin and theopenclawpackage from public registries. - [COMMAND_EXECUTION]: The documentation provides multiple shell commands for managing the OpenClaw gateway, modifying system configurations, and setting up systemd services and firewall rules using sudo.
- [PROMPT_INJECTION]: The skill facilitates the handling of incoming messages from WeChat, which presents a surface for indirect prompt injection attacks where an external sender could attempt to influence the agent's behavior.
- Ingestion points: External message text and images enter the agent context via the webhook listener described in SKILL.md.
- Boundary markers: No delimiters or safety instructions are defined to help the agent distinguish between legitimate commands and external message content.
- Capability inventory: The skill can manage gateway processes, access local configuration files (~/.openclaw/openclaw.json), and send messages or media back to the WeChat channel.
- Sanitization: There are no documented procedures for validating or sanitizing incoming message content before it is processed by the AI.
Audit Metadata