prompt-engineering

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

• Third-party content exposure detected (high risk: 0.90). The skill explicitly instructs using Grok's real-time X (Twitter) access and web search/tool use (see SKILL.md model summary and references/grok.md, plus ReAct/Parallel Tool Use examples) so the agent is expected to ingest and act on untrusted public social-media/web content.