Hackread.com<p>AgentSmith flaw in LangSmith’s Prompt Hub exposed user API keys and data via malicious AI agents using hidden proxies, researchers reveal.</p><p>🔗 <a href="https://hackread.com/agentsmith-flaw-langsmith-prompt-hub-api-keys-data/" rel="nofollow noopener" translate="no" target="_blank"><span class="invisible">https://</span><span class="ellipsis">hackread.com/agentsmith-flaw-l</span><span class="invisible">angsmith-prompt-hub-api-keys-data/</span></a></p><p><a href="https://mstdn.social/tags/CyberSecurity" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>CyberSecurity</span></a> <a href="https://mstdn.social/tags/LangSmit" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>LangSmit</span></a> <a href="https://mstdn.social/tags/AgentSmith" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>AgentSmith</span></a> <a href="https://mstdn.social/tags/Vulnerability" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>Vulnerability</span></a> <a href="https://mstdn.social/tags/AI" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>AI</span></a></p>