gate-info-coinanalysis

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

• Third-party content exposure detected (high risk: 0.90). The skill's required workflow (SKILL.md Step 2 and the tool table) calls news_feed_search_news and news_feed_get_social_sentiment to ingest public news articles and Twitter/social media sentiment, which the LLM must read and aggregate into its analysis, exposing the agent to untrusted third-party content that could carry indirect prompt injections.