The 31 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 EMBRACE: Codex embedded browser reads files outside the project via malicious HTML
- 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 Anthropic Claude model develops working Linux kernel MPTCP root exploit (CVE-2026-98432)
- 2026-10-27 Perplexity Comet browser agent bypasses file:// hard boundary twice, enabling local file exfiltration and 1Password vault takeover
- 2026-10-25 Deloitte WA university merger feasibility report contained AI-hallucinated references and $260m–$311m cost discrepancies
- 2026-10-23 GPT-6.1 Sol agent disabled security alerts during evaluation-pipeline repair
- 2026-10-22 METR red-team finds vulnerabilities in OpenAI monitoring system
- 2026-10-21 Grieving mother seeks answers from OpenAI over son's ChatGPT use
- 2026-10-21 Google SynthID Detector flags apparently real images, per Full Fact investigation
- 2026-10-20 OPPO Find X10 Manus AI agent email access: indirect prompt injection vulnerability disclosed
- 2026-10-20 WhatsApp support chatbot instructed by hidden help-page text not to recommend privacy regulators
- 2026-10-19 WhatsApp help pages exposed hidden instructions for Meta chatbot
- 2026-10-15 Langflow exploited in 1,423 honeypot attack attempts
- 2026-10-15 Waymo robotaxi strikes and kills cat KitKat in San Francisco
- 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)
- 2026-10-04 Indirect prompt injection in Manus AI agent leads to reverse shell and credential exposure
- 2026-10-02 ChatGPT macOS app vulnerability exposed conversations, since fixed
- 2026-10-01 Guardian test: ChatGPT and Grok remove hijab from AI-generated image of Muslim woman
- 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
- 2026-09-21 Malicious HEIF upload reached OpenAI internal GitHub
- 2026-09-21 Researchers break out of OpenAI Codex sandbox twice
- 2026-09-20 Zhipu ZCode repository snapshot upload without clear consent
- 2026-09-19 BragJack malicious browser extensions hijack AI agents across five browsers
- 2026-09-18 Hacktron researchers use Claude to access OpenAI employee ChatGPT accounts
- 2026-09-17 Hackers turn AI agent into cyber weapon by deleting safety refusals
- 2026-09-11 Agent swarm attributed to OpenAI published thousands of RubyGems packages, gained RCE on RubyDoc.info, and attempted API-key theft
- 2026-08-27 Claude sandbox DNS exfiltration via indirect prompt injection from Google Drive document
- 2026-08-06 Atlassian Rovo prompt injection exfiltrated Jira and Confluence data