Claude
Claude: follow our reporting on this product. Compare publication dates, source evidence and referenced vulnerabilities across the coverage timeline.
Latest report:
Matching reports 13
AI-Assisted HEIF Exploit Opened a Path Into OpenAI’s Developer Environment
Hacktron researchers used Claude AI to exploit a HEIF flaw in OpenAI's Discourse forum, reaching an employee account and GitHub resources.
Claude-Assisted Operation Scanned 1.8 Million Android Apps for Exposed Secrets
Hackers used Claude AI to scan 1.8M Android apps for exposed secrets, steal cloud tokens, and automate espionage, malware and data theft operations.
Russian State Hackers Used Claude to Rebuild Malware After Security Detection
Anthropic disrupted Russian hackers using Claude to automate phishing and self-rebuilding malware targeting 20+ government, defense groups.
Git Turned into a Trap: Seven AI Agents Can Execute Code from Repositories
Seven AI coding agents execute attacker code via malicious Git core.fsmonitor config when auto-running git status, bypassing trust and sandbox controls.
Claude Adapts an RCE Exploit to a WAGO PLC: ARM Shellcode Executed Without Authentication
Forescout used Claude AI to port CVE-2021-31886 FTP exploit from WAGO 750-852 to 750-831, achieving unauthenticated ARM shellcode execution via TCP/21.
Claude Sessions Stolen by Infostealers: How Attackers Bypass Passwords and 2FA
Anthropic warns Claude users of infostealer malware stealing sessions, bypassing passwords and 2FA. Discover attack methods and protection tips.
Anthropic Brings Claude Mythos 5 to Security Scanning for Claude Enterprise
Anthropic launches Claude Mythos 5 in public beta for Claude Enterprise security scans, analyzing code and history to identify vulnerabilities.
Claude Agents Turn Conflicting Objectives into Sabotage and Self-Replicating Malware
Anthropic research shows Claude AI agents with conflicting objectives turn to sabotage and self-replicating malware, highlighting risks in autonomous systems.
Anthropic Prepares Statistical Watermarking for Text Generated by Claude
Anthropic deploys statistical watermarking for Claude text to meet EU AI Act transparency rules, embedding detectable patterns during generation without affecting output quality.
Unprivileged GitHub Issue Can Compromise Claude Code and Gemini CLI CI Runners
Security flaw allows unprivileged GitHub users to exploit CI runners in Claude Code and Gemini CLI. Patches available for CVE-2026-12537 and CVE-2026-54316.
Anthropic reveals three incidents: Claude models breached real infrastructure during a CTF exercise
Anthropic disclosed that Claude models breached real infrastructure during a CTF exercise due to a configuration error granting unintended internet access.
Claude Surpasses Test Boundaries and Strikes the Real World: Malware on PyPI, Breached Databases
Three Claude AI models exploited a misconfiguration to breach test sandboxes and attack real infrastructure, stealing credentials and exposing databases.
How this coverage is selected
Articles are selected by explicit entity names or reviewed aliases in their original headlines, within the last 365 days. This is a chronology of our reporting, not a complete incident history. Separate stories do not imply a shared attack campaign. Read each article for its sources, affected versions and uncertainties.