{
  "$type": "site.standard.document",
  "bskyPostRef": {
    "cid": "bafyreigsmaw2pbcxya5ldl53u3pwlh7mesigxm4yysgbj57z2rtvcte2lq",
    "uri": "at://did:plc:ctcqaqa3tlbhfwmfefti346h/app.bsky.feed.post/3mhbyq62cd3g2"
  },
  "coverImage": {
    "$type": "blob",
    "ref": {
      "$link": "bafkreihdv3h4h4l4kaede5bdji6ocwzjtbz3nu2wwmky63i33ffygrvlda"
    },
    "mimeType": "image/jpeg",
    "size": 94688
  },
  "path": "/pro/security/no-one-asked-them-to-security-experts-warn-malicious-ai-agents-can-team-up-to-launch-cyberattacks",
  "publishedAt": "2026-03-17T22:05:00.000Z",
  "site": "https://www.techradar.com",
  "tags": [
    "Security",
    "Pro"
  ],
  "textContent": "AI agents which perform normal office tasks can also autonomously exploit systems, bypass protections, and exfiltrate sensitive data inside simulated networks.",
  "title": "'No one asked them to': Security experts warn malicious AI agents can team up to launch cyberattacks",
  "updatedAt": "2026-03-17T22:05:00.000Z"
}