wechat-channels-profile

MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).

• Third-party content exposure detected (high risk: 0.85). The required runtime workflow calls TikHub MCP tools (wechat_channels_fetch_user_search and fallback wechat_channels_fetch_search_ordinary) via callTool(), which returns JSON parsed from the tool’s structuredContent/content text; that tool-provided free-form profile/video text is outsider-authored content that the script then injects into the agent’s LLM context through the agent’s tool results.