{
  "$type": "site.standard.document",
  "bskyPostRef": {
    "cid": "bafyreifrj3ja4kfqvevk5f7eos3xlu6i3lqhen2mdbdfroq7ywju55gvce",
    "uri": "at://did:plc:6wtxqaikjf62unmnajbfbq5v/app.bsky.feed.post/3mgfd5hm744k2"
  },
  "coverImage": {
    "$type": "blob",
    "ref": {
      "$link": "bafkreifs3y7pqfoehoykhd3jk5pru3rpfqgxfw3y5bofwnocstuvxo5e6i"
    },
    "mimeType": "image/webp",
    "size": 37056
  },
  "path": "/indirect-prompt-injection-attacks-are-no-longer-theoretical-and-ai-agents-now-face-real-abuse-on-live-websites/",
  "publishedAt": "2026-03-06T09:12:09.000Z",
  "site": "https://vpncentral.com",
  "tags": [
    "News",
    "Indirect prompt injection attacks are no longer theoretical, and AI agents now face real abuse on live websites",
    "VPN Central"
  ],
  "textContent": "Indirect prompt injection is now a real-world security problem, not just a lab concept. Palo Alto Networks Unit 42 says attackers have already deployed web-based indirect prompt injection attacks on live websites, where hidden instructions inside normal-looking content can manipulate AI systems that summarize pages, review ads, or process web content automatically. The core issue […]\n\nThe post Indirect prompt injection attacks are no longer theoretical, and AI agents now face real abuse on live websites appeared first on VPN Central.",
  "title": "Indirect prompt injection attacks are no longer theoretical, and AI agents now face real abuse on live websites"
}