xai-auth

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

• Third-party content exposure detected (high risk: 0.90). The skill instructs Grok to search and summarize public social media and web content (see search_x, analyze_sentiment, stock_sentiment, crypto_sentiment, and web_search which invoke Twitter/X and web searches), so it ingests untrusted user-generated content that could contain indirect prompt injections.