gate-news-communityscan

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

• Third-party content exposure detected (medium risk: 0.30). The agent skill uses MCP tool news_feed_search_x to search and fetch user-generated posts and KOL commentary from X/Twitter without prior item selection.

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

• Potentially malicious external URL detected (medium risk: 0.30). The skill includes automated update scripts that fetch and execute remote code and skill updates from GitHub repositories (gate/gate-skills), representing an unverifiable runtime external dependency from a common third-party/unofficial source.