51mee-position-parse

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

• Third-party content exposure detected (high risk: 1.00). This skill directly ingests arbitrary user-provided job descriptions (see SKILL.md step "接收文本
• 用户提供职位描述" and the prompt template that embeds {职位描述文本}), which are untrusted user-generated content fed into the LLM and can carry indirect prompt-injection instructions that affect the model's outputs.