linkedin-jobs-search

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

• Third-party content exposure detected (high risk: 0.85). Outsider-authored free text is ingested from LinkedIn job postings (publicly authored by third-party employers) via runtime fetch calls to /voyager/api/voyagerJobsDashJobCards and /voyager/api/jobs/jobPostings/{job_id}; the returned JSON includes fields like title, company, and especially description which are then placed into the agent’s LLM context through the skill’s output.