daangn-used-goods-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 reads public used-goods listings and detail pages from Daangn via URL/search queries, which are outsider-authored marketplace content fetched via active user/agent search.

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

• Potentially malicious external URL detected (high risk: 0.70). The skill fetches instructions and updates from an external npm package (@nomadamas/k-skill) hosted on an unofficial personal GitHub repository/npm channel during setup and runtime.