{
  "$type": "site.standard.document",
  "bskyPostRef": {
    "cid": "bafyreie5zhbpyirnfdqj7wqey5s7vbqjmoi2l356dtsowj3fsu5cmy4634",
    "uri": "at://did:plc:ghkvexthfanuyq7fb5veq6tw/app.bsky.feed.post/3mhbnvdcg2ap2"
  },
  "coverImage": {
    "$type": "blob",
    "ref": {
      "$link": "bafkreibe6lzoszieqm46y6mktku5m336kqsf6a7552xbtceua4lsjatitm"
    },
    "mimeType": "image/jpeg",
    "size": 380917
  },
  "path": "/2026/03/ai-flaws-in-amazon-bedrock-langsmith.html",
  "publishedAt": "2026-03-17T16:39:00.000Z",
  "site": "https://thehackernews.com",
  "textContent": "Cybersecurity researchers have disclosed details of a new method for exfiltrating sensitive data from artificial intelligence (AI) code execution environments using domain name system (DNS) queries.\nIn a report published Monday, BeyondTrust revealed that Amazon Bedrock AgentCore Code Interpreter's sandbox mode permits outbound DNS queries that an attacker can exploit to enable interactive shells",
  "title": "AI Flaws in Amazon Bedrock, LangSmith, and SGLang Enable Data Exfiltration and RCE"
}