resume

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

• Third-party content exposure detected (high risk: 0.90). The SKILL.md explicitly requires importing and scanning user-provided LinkedIn/profile URLs and job-description URLs ("Import and scan any attached resume/LinkedIn or job description to extract data and keywords" and example prompts like "here's my LinkedIn URL" / "[JD URL]"), which are arbitrary public third‑party sources whose content the agent will read and use to tailor the CV and drive follow-up actions (keyword alignment and edits), enabling indirect prompt injection risk.