daangn-jobs-search

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

• Third-party content exposure detected (low risk: 0.10). The agent searches public job postings and reads job detail pages from Daangn Market via user-selected keywords and URLs.

MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).

• Potentially malicious external URL detected (high risk: 0.70). The skill uses npm to fetch and execute a remote CLI package from a third-party repository (@nomadamas/k-skill), which constitutes an unverifiable runtime external dependency.