recruitment-processor

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

• Third-party content exposure detected (high risk: 0.90). Flagged because the SKILL.md workflow (step 2.1) explicitly scans markdown image references in the form ![alt](url) and "使用图像识别能力提取每张图片中的文字信息", which requires fetching and interpreting images referenced by arbitrary URLs (potentially untrusted third-party content) and using that extracted text to drive extraction and filtering decisions.