daangn-jobs-search

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

• Third-party content exposure detected (high risk: 0.80). The skill explicitly fetches and ingests public, user-generated content from daangn.com (e.g., the region resolver API at https://www.daangn.com/kr/api/v1/regions/keyword, the jobs _data route /kr/jobs/?...&_data=routes/kr.jobs._index, and parse_html_detail which reads page HTML/meta/JSON-LD), and it reads and interprets that untrusted third‑party content as part of its search/detail workflow, so such content could influence the agent's outputs and next actions.