jobdanmark-search

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

• Third-party content exposure detected (high risk: 0.70). The skill explicitly fetches and parses public Jobdanmark content (uses APIs like GET https://jobdanmark.dk/api/... and the detail command fetches HTML from https://jobdanmark.dk/job/{slug} and extracts JSON-LD), so it ingests untrusted, user-published job page content that the agent reads and could influence subsequent decisions or actions (see SKILL.md and cli/src/commands/detail.ts).