The 32 incidents behind this number
Data built 2026-11-16T15:22:29Z
- 2026-10-30 Trezor Safe 5 from reseller CryptoBilis found with implant board exfiltrating recovery phrase over cellular network
- 2026-10-29 Claude agent detects MeshAgent screen-capture malware on high-stakes poker player's machine
- 2026-10-28 Cathedral AI agents breach Anthropic internal systems via third-party business software
- 2026-10-27 Perplexity Comet browser agent bypasses file:// hard boundary twice, enabling local file exfiltration and 1Password vault takeover
- 2026-10-26 Anthropic's Claude agent autonomously accessed Georgia voter data hub and bypassed a paywall
- 2026-10-25 Unauthorized third-party AI agents detected operating inside US bank customer accounts
- 2026-10-24 Russian-linked AI deepfake campaign targets Texas candidate James Talarico
- 2026-10-23 KOP Mall worker accused of upskirt photos and AI child sexual abuse material
- 2026-10-23 Garage-built ChatGPT-controlled smart rifle fires on voice command; OpenAI revokes engineer's access
- 2026-10-22 302.ai public Azure bucket exposed 17.6 million files including 144,000 AI chat logs
- 2026-10-21 Hackers use Claude and Grok agents in attacks on Latin American banks
- 2026-10-21 Stolen Anthropic and OpenAI API keys fuel model distillation black market
- 2026-10-21 Storm-0940 uses ARTEX agentic AI framework to automate cross-tenant password spraying and OAuth application abuse
- 2026-10-18 OpenCode large-scale distillation attack compromises 1.4% of Console users, stolen API keys used for unauthorised charges
- 2026-10-17 ChatGPT advised Tumbler Ridge school shooter on mass murder before February 2026 attack
- 2026-10-15 Character.AI chatbots promoted as therapists/psychologists; states cite 2024 wrongful-death suit and privacy concerns in bankruptcy filing
- 2026-10-10 AgentCorruption: prompt-injected Bedrock AgentCore agent exfiltrates execution-role credentials via IMDS
- 2026-10-09 Public-facing AWS agent could read, rewrite or delete other agents in its region (Amazon Bedrock AgentCore)
- 2026-10-07 Yoido Full Gospel Church (Seoul) customer and member database breach, 850,000 members potentially affected, AI sub-agent traces found
- 2026-10-05 Shinhan Bank data breach with suspected AI-assisted intrusion
- 2026-09-29 Connecticut pro se plaintiff sanctioned for prompt injection against court AI tool
- 2026-09-24 Reno face recognition arrest case draws Innocence Project and civil liberties groups
- 2026-09-18 Hacktron researchers use Claude to access OpenAI employee ChatGPT accounts
- 2026-09-15 Russia-linked cyberespionage group used Claude to reverse-engineer military drone firmware
- 2026-09-11 Agent swarm attributed to OpenAI published thousands of RubyGems packages, gained RCE on RubyDoc.info, and attempted API-key theft
- 2026-09-10 Chinese labs distillation attacks against Claude
- 2026-09-10 Anthropic reports blocking scientists' attempts to use Claude in ways that could support biological weapons development
- 2026-09-03 Grok alleged to have generated sexualized images of abuse victims
- 2026-09-01 Attackers steal METR API key and burn $600,000 in AI credits
- 2026-08-27 Northern Illinois University student accused of using Grok to generate child sexual abuse material in dorm room
- 2026-08-18 AI-assisted change introduced a script-injection flaw in a Snowflake GitHub workflow, later exploited by an autonomous research agent
- 2026-08-17 AI-assisted state-aligned espionage campaign against UAE critical sectors