{
"$type": "site.standard.document",
"bskyPostRef": {
"cid": "bafyreigbw6ul4ezuhjtk2m2ttdgqxgjheetugkmfquhwncpww45ifvxiw4",
"uri": "at://did:plc:ctcqaqa3tlbhfwmfefti346h/app.bsky.feed.post/3mhgfkpfapqz2"
},
"coverImage": {
"$type": "blob",
"ref": {
"$link": "bafkreifkawc7wgoxqaomiiq5rlg7mpa3ph6hwaqcorhti65yp4vqllu5ci"
},
"mimeType": "image/jpeg",
"size": 87269
},
"path": "/pro/security/three-high-risk-ai-vulnerabilities-discovered-in-claude-ai-end-to-end-attack-chain-exfiltrates-sensitive-info-without-user-knowing",
"publishedAt": "2026-03-19T16:00:00.000Z",
"site": "https://www.techradar.com",
"tags": [
"Security",
"Pro"
],
"textContent": "A legitimate Google ad could lead to data exfiltration through a chain of Claude flaws.",
"title": "Three high-risk AI vulnerabilities discovered in Claude.ai – end-to-end attack chain exfiltrates sensitive info without user knowing"
}