{
  "$type": "site.standard.document",
  "bskyPostRef": {
    "cid": "bafyreidl5fw75dtxei27ndgtprfnjlyv7ehgpdk7lwwdfukmayvn7cbexy",
    "uri": "at://did:plc:gapzbf5nl5wxaqkqoecaeawh/app.bsky.feed.post/3mfspyins3yq2"
  },
  "path": "/security-flaws-in-anthropics-claude-code-risk-stolen-data-system-takeover/",
  "publishedAt": "2026-02-26T14:36:01.000Z",
  "site": "https://devops.com",
  "tags": [
    "AI",
    "Blogs",
    "Business of DevOps",
    "DataOps",
    "DevSecOps",
    "Features",
    "News",
    "Social - Facebook",
    "Social - LinkedIn",
    "Social - X",
    "AI API Security",
    "AI coding risks",
    "AI coding tools",
    "AI developer tools",
    "Anthropic Claude Code",
    "Check Point",
    "MCP protocol",
    "Palo Alto Unit 42"
  ],
  "textContent": "Three critical vulnerabilities found in Anthropic’s Claude Code agentic AI developer tool could be exploited simply by cloning and opening an untrusted project and lead to system takeover, stolen API keys, and credential theft, according to security researchers with Check Point. The security flaws, which Anthropic fixed last year and last month after the researchers […]",
  "title": "Security Flaws in Anthropic’s Claude Code Risk Stolen Data, System Takeover"
}