naver-blog-research

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

• Third-party content exposure detected (low risk: 0.10). The skill searches Naver blogs and reads blog post content from arbitrary URLs fetched via Naver search or user-provided links, exposing the agent to outsider-authored free text on blogs.

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

• Potentially malicious external URL detected (high risk: 0.70). The skill instructs execution of remote npm packages from an external registry (@nomadamas/k-skill) during setup and runtime, representing an unverifiable third-party operational dependency under weak/unknown provenance.