{
"$type": "site.standard.document",
"bskyPostRef": {
"cid": "bafyreibagtzjkk352z3wnnjhzcpdzvqzqusfypzra2jje6hu4gggavarye",
"uri": "at://did:plc:ghkvexthfanuyq7fb5veq6tw/app.bsky.feed.post/3mfpebpyixuu2"
},
"coverImage": {
"$type": "blob",
"ref": {
"$link": "bafkreiayjkrihasbljj6spy55drweqlqeyr3m3am62vyqvpquubvirhb4q"
},
"mimeType": "image/jpeg",
"size": 150044
},
"path": "/2026/02/claude-code-flaws-allow-remote-code.html",
"publishedAt": "2026-02-25T17:00:00.000Z",
"site": "https://thehackernews.com",
"textContent": "Cybersecurity researchers have disclosed multiple security vulnerabilities in Anthropic's Claude Code, an artificial intelligence (AI)-powered coding assistant, that could result in remote code execution and theft of API credentials.\n\"The vulnerabilities exploit various configuration mechanisms, including Hooks, Model Context Protocol (MCP) servers, and environment variables – executing",
"title": "Claude Code Flaws Allow Remote Code Execution and API Key Exfiltration"
}