product

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

• Third-party content exposure detected (high risk: 0.80). The skill calls the public API https://api.fore.vip/mcp/query_kl (see SKILL.md "Call MCP Server") and explicitly reads and displays product "content" and URLs (see "Handle response" / "Display products"), which are user-generated/untrusted fields that can contain prompt-like instructions and thus could influence the agent's subsequent actions.