apply

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

• Third-party content exposure detected (high risk: 1.00). The skill explicitly navigates to and fetches arbitrary job posting pages from the open web (see SKILL.md Step 1 "If a URL: ... fetch the posting" and Step 3 "navigate to the URL, take a screenshot / read_page(filter='interactive')"), then reads and uses that posting to tailor resumes and decide form-filling actions (Step 4), so untrusted third-party content can influence agent behavior.