jobkorea-talent-search

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

• Third-party content exposure detected (low risk: 0.10). The skill searches and ingests public talent listings and profile summaries from JobKorea via browser navigation and script execution, where user profiles and resumes can contain arbitrary outsider-authored text.

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

• Potentially malicious external URL detected (high risk: 0.70). The skill instructs the agent to download and execute code from an external remote registry (https://github.com/NomaDamas/k-skill) via npx, which is an unverified external runtime dependency.