{
"$type": "site.standard.document",
"bskyPostRef": {
"cid": "bafyreidkdcl72xhb2iej3u3zpoii7k7hskdevlkgpq6bvqmoxmvmgebaoe",
"uri": "at://did:plc:ghkvexthfanuyq7fb5veq6tw/app.bsky.feed.post/3mh24rok6pjp2"
},
"coverImage": {
"$type": "blob",
"ref": {
"$link": "bafkreidisp5csqvhmfmgt54564pkdygrdcnwtttscvyt4npq7jh5bshjw4"
},
"mimeType": "image/jpeg",
"size": 413454
},
"path": "/2026/03/openclaw-ai-agent-flaws-could-enable.html",
"publishedAt": "2026-03-14T16:17:00.000Z",
"site": "https://thehackernews.com",
"textContent": "China's National Computer Network Emergency Response Technical Team (CNCERT) has issued a warning about the security stemming from the use of OpenClaw (formerly Clawdbot and Moltbot), an open-source and self-hosted autonomous artificial intelligence (AI) agent.\nIn a post shared on WeChat, CNCERT noted that the platform's \"inherently weak default security configurations,\" coupled with its",
"title": "OpenClaw AI Agent Flaws Could Enable Prompt Injection and Data Exfiltration"
}