job-posting-match

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

• Third-party content exposure detected (high risk: 0.85). Runtime path: the skill fetches public JobKorea/Saramin search result HTML pages (outsider-authored web content) via fetch() → search_jobkorea()/search_saramin() → parse_jobkorea()/parse_saramin(), then converts scraped text into LLM-readable fields (title, company, summary) that are included in the final output context.