{
"$type": "site.standard.document",
"bskyPostRef": {
"cid": "bafyreiafzwy6f26rqxzzqyeodwqwvh55qzi7xucytbqe7qymkzipugesom",
"uri": "at://did:plc:6wtxqaikjf62unmnajbfbq5v/app.bsky.feed.post/3mk42uyy6sg42"
},
"coverImage": {
"$type": "blob",
"ref": {
"$link": "bafkreihkjojxpxvzy53gz6u6x7cq4ec6r2ggvvw6ys5olrjnwnj5fni6ya"
},
"mimeType": "image/webp",
"size": 31204
},
"path": "/malicious-gguf-models-could-give-attackers-rce-on-sglang-inference-servers/",
"publishedAt": "2026-04-22T10:43:08.000Z",
"site": "https://vpncentral.com",
"tags": [
"News",
"Malicious GGUF models could give attackers RCE on SGLang inference servers",
"VPN Central"
],
"textContent": "A critical flaw in SGLang could let attackers turn a standard GGUF model file into a remote code execution path on AI inference servers. The bug, tracked as CVE-2026-5760, affects SGLang’s /v1/rerank endpoint and can execute attacker-controlled Python code when the server loads a poisoned model and processes a rerank request. The issue matters because […]\n\nThe post Malicious GGUF models could give attackers RCE on SGLang inference servers appeared first on VPN Central.",
"title": "Malicious GGUF models could give attackers RCE on SGLang inference servers"
}