The 108 incidents behind this number
Data built 2026-11-16T15:22:29Z
- 2026-10-31 ChatGPT shared-link Preview sandbox escape via MathLive postMessage listener
- 2026-10-30 SolanaCry fake GitHub repo tricks AI coding agents into installing NetSupport RAT
- 2026-10-30 Malicious Hugging Face 'Qwen2 test' models execute hidden crypto miner and reverse shell via trust_remote_code
- 2026-10-30 EMBRACE: Codex embedded browser reads files outside the project via malicious HTML
- 2026-10-30 Deepfake liveness-check bypass attempts at Indonesian bank's digital KYC
- 2026-10-30 Trezor Safe 5 from reseller CryptoBilis found with implant board exfiltrating recovery phrase over cellular network
- 2026-10-30 Backdoored Anthropic Claude VS Code extension on Cursor marketplace (v2.1.313) installs SSH backdoor for up to 5,000 developers
- 2026-10-29 Unauthorized relay service reconfigures genuine Codex and Claude Code CLIs, disabling sandboxes and replacing credentials
- 2026-10-28 Microsoft Tay chatbot suspended after inflammatory tweets from coordinated attack
- 2026-10-28 LiteLLM master key exposure leads to GitHub org-owner token theft and poisoned release artifacts
- 2026-10-28 Malicious startup hooks in 42 hijacked GitHub repositories execute payload when AI coding assistants open a workspace
- 2026-10-27 Perplexity Comet browser agent bypasses file:// hard boundary twice, enabling local file exfiltration and 1Password vault takeover
- 2026-10-26 Malicious AGENTS.md in Downloads folder hijacks Codex and Claude Code agents
- 2026-10-23 Chat agent socially engineered into revealing a long-lived OAuth token; CRM data of more than 700 companies reportedly at risk
- 2026-10-21 Stolen Anthropic and OpenAI API keys fuel model distillation black market
- 2026-10-20 OPPO Find X10 Manus AI agent email access: indirect prompt injection vulnerability disclosed
- 2026-10-18 OpenCode large-scale distillation attack compromises 1.4% of Console users, stolen API keys used for unauthorised charges
- 2026-10-16 Eiliko AI robot toy: remote hijack and exposed conversations and child profiles
- 2026-10-15 Langflow exploited in 1,423 honeypot attack attempts
- 2026-10-15 Critical ChatGPT GitHub Connector flaw could leak private repository secrets
- 2026-10-15 Indirect prompt injection attempts embedded in HTTP response headers across websites
- 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 Agentjacking demonstration against Fortune 100 company hijacks over 100 agents via injectable Sentry DSNs
- 2026-10-07 Prompt-injected email assistant summary pushes employee toward fraudulent vendor payment
- 2026-10-06 GitHub Copilot CLI prompt-injection flaw lets a web page steer the agent to steal local secrets
- 2026-10-04 Indirect prompt injection in Manus AI agent leads to reverse shell and credential exposure
- 2026-10-03 Microsoft reports 50 prompt-based attempts to poison AI assistant memory across 31 companies
- 2026-10-02 Langflow 12th exploited CVE of 2026 fuels credential harvesting campaign
- 2026-10-02 ChatGPT macOS app vulnerability exposed conversations, since fixed
- 2026-09-30 Jailbroken Kimi models gave bioweapon instructions, BBC finds
- 2026-09-29 Connecticut pro se plaintiff sanctioned for prompt injection against court AI tool
- 2026-09-24 SalesBleed: 0-click data exfiltration from Salesforce Agentforce via indirect prompt injection in Web-to-Lead form
- 2026-09-22 Meta Muse zero-day let attackers hijack AI assistant via hidden setting
- 2026-09-19 BragJack malicious browser extensions hijack AI agents across five browsers
- 2026-09-18 Shai-Hulud worm spreads from hijacked AI coding-assistant session at a SaaS provider
- 2026-09-16 Shai-Hulud worm spreads via hijacked AI coding assistant session
- 2026-09-10 Chinese labs distillation attacks against Claude
- 2026-09-08 ChatGPT flaw let attackers read victims' Gmail through hidden channel
- 2026-09-01 Claude Code Auto Mode: website summary leads to remote code execution via Python module shadowing
- 2026-09-01 Russia-aligned UAC-0099 prompt injection against AI malware analysis (GuardBreaker)
- 2026-09-01 Attackers steal METR API key and burn $600,000 in AI credits
- 2026-08-27 Claude sandbox DNS exfiltration via indirect prompt injection from Google Drive document
- 2026-08-20 Grok chat data exfiltration via encrypted prompt injection (Cryptographic Context Injection)
- 2026-08-06 Atlassian Rovo prompt injection exfiltrated Jira and Confluence data
- 2026-08-06 Typosquatted agent skills trojanized to deliver credential-harvesting infostealer
- 2026-08-05 Claude in Chrome indirect prompt injection chain: inbox exfiltration, Drive persistence and account takeover
- 2026-08-05 Intent collision via X comment hijacks ChatGPT Atlas into mass WhatsApp phishing from victim's account
- 2026-07-23 AgentForger: CSRF via ChatGPT Workspace Agents Builder URL parameters forges attacker-controlled autonomous agent
- 2026-07-21 Hidden web text hijacks AWS Kiro IDE to run attacker code
- 2026-07-20 FakeGit campaign targets AI coding agents with malicious GitHub repos
- 2026-07-17 Cursor git.exe repo-poisoning zero-day patched without advisory or CVE
- 2026-07-13 Ghostcommit attack hides malicious AI instructions in images
- 2026-07-08 HalluSquatting: hallucinated resource names lead AI coding assistants to install botnet malware (research demonstration)
- 2026-07-07 GitLost: public GitHub issue tricks GitHub Agentic Workflows agent into leaking private repos
- 2026-06-30 GuardFall: shell-trick bypass of AI coding agent command guards
- 2026-06-28 SearchLeak flaw in Microsoft 365 Copilot exposed data
- 2026-06-25 Mercor breached through compromised LiteLLM PyPI releases (TeamPCP)
- 2026-06-17 Mastra npm packages backdoored in supply chain attack attributed to North Korea
- 2026-06-16 Google Vertex AI SDK flaw let attackers hijack model uploads via bucket squatting
- 2026-06-12 Agentjacking attack tricks AI coding agents into running malicious code
- 2026-06-09 OpenClaw AI email agent falls for phishing simulations and sends sensitive data to an external account
- 2026-06-06 Miasma worm compromises 73 Microsoft GitHub repositories via AI coding tools
- 2026-06-06 Claude Code GitHub Action prompt-injection flaw could expose GitHub credentials
- 2026-06-05 Miasma worm supply chain attack targets Microsoft Azure repositories and AI coding tools (June 5, 2026)
- 2026-06-05 Hugging Face Transformers flaw enables remote code execution
- 2026-06-04 Gemini voice assistant hijacked via messaging notifications
- 2026-06-01 OpenAI Codex authentication tokens stolen via malicious npm package codexui-android
- 2026-05-27 AI-generated npm malware targets Claude user files and leaks its GitHub token
- 2026-05-09 Chinese grey market resells Claude API access using stolen credentials
- 2026-05-07 Grok and Bankr prompt-injected via Morse code to transfer DRB tokens; 14 Bankr wallets later drained
- 2026-05-04 Users tricked Grok into sending crypto through hidden code and encoded prompts
- 2026-04-23 Claude Mythos accessed by unauthorized group via leaked naming and contractor login
- 2026-04-21 Unauthorized users accessed Anthropic's Mythos model
- 2026-04-20 Vercel breach via third-party AI tool Context.ai with broad Google Workspace OAuth access
- 2026-04-19 Vercel April 2026 security incident: breach via compromised Context.ai third-party AI tool
- 2026-04-01 Persistent memory compromise found in Claude Code
- 2026-03-27 LangChain and LangGraph flaws expose files, secrets and databases
- 2026-03-20 Heidi Health AI scribe jailbroken in New Zealand emergency departments
- 2026-03-20 McKinsey AI chatbot Lilli breached via exposed endpoints and SQL injection
- 2026-03-17 CursorJack: MCP deeplink abuse in Cursor IDE (proof of concept)
- 2026-03-11 Researchers trick Perplexity Comet browser into phishing scam
- 2026-03-09 McKinsey Lilli chatbot breached by red-team AI agent in two hours
- 2026-03-03 Perplexity Comet browser flaws allow local file access and 1Password takeover
- 2026-02-25 GitHub Copilot RoguePilot passive prompt injection repository takeover
- 2026-02-23 SANDWORM_MODE npm worm targets AI packages and spreads via MCP server
- 2026-02-20 hackerbot-claw AI bot actively exploits GitHub Actions workflows
- 2026-02-17 Cline CLI supply chain attack installs OpenClaw on developer systems
- 2026-02-13 Orchids vibe-coding platform zero-click compromise demonstrated to BBC reporter
- 2026-02-12 Attempted model extraction of Google Gemini through more than 100,000 prompts
- 2026-02-10 Google Translate Gemini mode vulnerable to prompt injection
- 2026-02-09 Tens of thousands of OpenClaw systems exposed by misconfigurations and known exploits
- 2026-02-02 OpenClaw one-click remote code execution via crafted malicious link (CVE-2026-25253)
- 2026-02-02 341 malicious ClawHub skills found stealing data from OpenClaw users
- 2026-02-01 ClawHavoc: 341 malicious skills on OpenClaw's ClawHub deliver infostealers
- 2026-01-27 Critical Clawdbot vulnerabilities found enabling cryptocurrency theft
- 2026-01-25 Prompt injection leads to simulated /etc/passwd disclosure
- 2026-01-24 Reprompt: a single malicious Copilot link could expose user data
- 2026-01-14 Reprompt attack enabled single-click data theft from Microsoft Copilot
- 2026-01-05 Researchers warn of data exposure risks in Claude Chrome extension
- 2025-12-26 Humanoid robots hacked through voice commands in demonstration
- 2025-12-24 Kuaishou livestream platform hit by AI-assisted bot attack
- 2025-12-16 Urban VPN Proxy Chrome extension harvested AI chat conversations
- 2025-12-01 OpenAI Codex CLI command injection via project-local MCP configuration (CVE-2025-61260)
- 2025-11-23 EchoLeak zero-click prompt injection exploit in Microsoft 365 Copilot
- 2025-11-12 Sora 2 audio output leaks hidden system prompt (Mindgard research, November 2025)
- 2025-11-05 Tenable finds seven ChatGPT vulnerabilities enabling data leaks and persistent hijacking
- 2025-11-03 Claude API flaw allows indirect prompt injection to steal user data