CVE-2026-25725
Vulnerability in Anthropic Claude Code
CVSS score
10.0
EPSS probability
%0.7
Risk score
0.1
Published
8 mo ago
Related Security News
Articles and analysis bulletins in which the press and security publications have covered this vulnerability:
Amazon Kiro Prompt Injection Can Exfiltrate Sensitive Data Through Kiro Powers
Cybersecurity researchers have disclosed details of a vulnerability in Amazon Kiro, an artificial intelligence (AI)-powered, agentic integrated development environment (IDE), that could facilitate data exfiltration via prompt injection and Kiro Powers. The security flaw, which does not have a CVE identifier, works against Kiro IDE 0.7.45 on Windows, according to Mindgard. The latest version of
Similar Vulnerabilities
8.8
CVE-2025-59536Code injection in Anthropic Claude Code
Patch status unknown Public Exploits:5EPSS %27
8.8
CVE-2026-55607Path traversal in Anthropic Claude Code
Patch status unknownEPSS %1
9.8
CVE-2025-64755OS command injection in Anthropic Claude Code
Patch status unknownEPSS %1
9.8
CVE-2025-65099Code injection in Anthropic Claude Code
Patch status unknownEPSS %1
8.8
CVE-2026-40068Improper input validation in Anthropic Claude Code
Patch status unknownEPSS %1
9.1
CVE-2026-54316Information exposure in Anthropic Claude Code
Patch status unknown Public Exploits:1EPSS %1
Get this vulnerability through the API
Affected products, version ranges, exploitation status and patch information in a single request, with a free key.
curl -H "x-api-key: $DAYBREACH_API_KEY" \ "https://api.daybreach.dev/api/v1/intel/cves/CVE-2026-25725"