{
"$type": "site.standard.document",
"bskyPostRef": {
"cid": "bafyreibgs56coaeehajrfl3kjcxc32hm2hxhoz2hpffkj53ryr3vtx42bq",
"uri": "at://did:plc:ghkvexthfanuyq7fb5veq6tw/app.bsky.feed.post/3mpjdgcygebq2"
},
"coverImage": {
"$type": "blob",
"ref": {
"$link": "bafkreiebmryq7h7z4ht3s777qrvfiks6435kxfiszzb4y4b3knj7nfz27a"
},
"mimeType": "image/jpeg",
"size": 421155
},
"path": "/2026/06/guardfall-exposes-open-source-ai-coding.html",
"publishedAt": "2026-06-30T14:26:15.000Z",
"site": "https://thehackernews.com",
"textContent": "The safety check that is supposed to stop an AI coding agent from running a dangerous command can be walked straight past using a shell trick that has been public for decades. New research from Adversa AI, which is named the bypass GuardFall, found it works against ten of the eleven popular open-source coding and computer-use agents the firm tested. Only one, \"Continue,\" was built to",
"title": "GuardFall Exposes Open-Source AI Coding Agents to Decades-Old Shell Injection Risks"
}