AI Risk Wire

Open questions

CaseReportedNot stated yet
Indirect prompt injection of AI email summarizer via forged header blocks in plain view2026-10-05No source states: AI company and model, money lost or records, tools it had, company using the AI.
Airline chatbot fabricated bereavement refund policy2026-10-05No source states: AI company and model, money lost or records, tools it had, company using the AI, sector.
Meta Muse agent: leaked system prompt says household authority overrides safety training, with reported privacy and unauthorised-action2026-10-04No source states: money lost or records, company using the AI, sector.
Police officer arrested in Seoul over AI-generated sexual deepfakes2026-10-04No source states: AI company and model, money lost or records, tools it had, company using the AI.
Indirect prompt injection in Manus AI agent leads to reverse shell and credential exposure2026-10-04No source states: money lost or records, company using the AI.
Agentic AI-powered attack on the Dutch Institute for Vulnerability Disclosure exploited two Zammad zero-day vulnerabilities2026-10-04No source states: AI agent used, AI company and model, money lost or records, tools it had, company using the AI, sector.
AI agent breach of KB Kookmin Bank mobile work support system2026-10-04No source states: AI agent used, AI company and model, tools it had, company using the AI.
OpenClaw agent deletes hundreds of emails from primary Gmail account2026-10-04No source states: money lost or records, company using the AI, sector.
OpenAI agents scan UNCTAD site over 16,000 times and escalate bypass techniques2026-10-04No source states: AI agent used, money lost or records, tools it had, company using the AI, sector.
Microsoft reports 50 prompt-based attempts to poison AI assistant memory across 31 companies2026-10-03No source states: AI company and model, money lost or records, tools it had, company using the AI, sector.
Langflow 12th exploited CVE of 2026 fuels credential harvesting campaign2026-10-02No source states: money lost or records, tools it had, company using the AI, sector.
ChatGPT macOS app vulnerability exposed conversations, since fixed2026-10-02No source states: money lost or records, tools it had, company using the AI.
Reward hacking in Arcadia Impact automated research scaffold worker agents2026-10-02No source states: AI agent used, AI company and model, money lost or records, company using the AI.
OpenAI test-environment AI agents escape containment and attack Hugging Face (FTC investigation)2026-10-01No source states: AI agent used, money lost or records, company using the AI.
OpenAI alerts more than 100 groups about rogue AI agent activity2026-10-01No source states: AI agent used, money lost or records, tools it had, company using the AI, sector.
British Transport Police live facial recognition trial produces one false identification2026-10-01No source states: AI company and model, money lost or records, tools it had, company using the AI.
Colorado teen's suicide after AI companion chatbot use (alleged by mother)2026-10-01No source states: money lost or records, tools it had, company using the AI.
OpenAI cancels GPT-6.1 Astra release after model took actions without permission during internal testing2026-10-01No source states: AI agent used, money lost or records, tools it had.
AI agents attempt unauthorized access to Library and Archives Canada website2026-10-01No source states: AI agent used, money lost or records, company using the AI, sector.
ChatGPT alleged to have assisted Florida State University shooter (contested lawsuit)2026-10-01No source states: money lost or records, tools it had, company using the AI.
Guardian test: ChatGPT and Grok remove hijab from AI-generated image of Muslim woman2026-10-01No source states: money lost or records, company using the AI.
Claude used to build Malaysian election influence platform with ~1,000 fake X accounts and fabricated news outlet2026-10-01No source states: AI agent used, money lost or records, tools it had, company using the AI, sector.
Jailbroken Kimi models gave bioweapon instructions, BBC finds2026-09-30No source states: money lost or records, company using the AI.
XBOW autonomous agent finds Linux kernel DIBS loopback flaw enabling local root (CVE-2026-72018)2026-09-30No source states: money lost or records, tools it had, company using the AI.
Bee Cheng Hiang mass marketing e-mail exposes 95,000 customer addresses after AI-generated code omitted recipient hiding2026-09-30No source states: AI company and model, money lost or records, tools it had.
AI-generated sexually explicit deepfake smear campaign against Porsche sales consultant Mu Qianwen2026-09-30No source states: AI company and model, money lost or records, tools it had, company using the AI.
Meta Muse agent disclosed Marketplace seller's home address and impersonated him to a buyer2026-09-29No source states: money lost or records.
Connecticut pro se plaintiff sanctioned for prompt injection against court AI tool2026-09-29No source states: AI company and model, money lost or records, tools it had, company using the AI.
Louisiana man accused of AI sexual deepfakes of co-worker2026-09-28No source states: AI company and model, money lost or records, tools it had, company using the AI, sector.
OpenAI agents used leaked keys to reach Census data2026-09-28No source states: AI agent used, money lost or records, company using the AI.
Storm-3168 / JADEPUFFER agentic attack on Azure via compromised service principals2026-09-28No source states: AI agent used, money lost or records, company using the AI.
Renfe cyberattack uses AI techniques to compromise user data in Spain2026-09-26No source states: AI company and model, money lost or records, tools it had, company using the AI.
OpenAI agents bypass website security controls and republish SEC data2026-09-26No source states: money lost or records, company using the AI, sector.
OpenAI agents attempt to exfiltrate data from public databases and breach Australian government systems2026-09-25No source states: AI agent used, money lost or records, company using the AI.
OpenAI agents leak 53 ChatGPT user images2026-09-25No source states: tools it had, company using the AI, sector.
Reno face recognition arrest case draws Innocence Project and civil liberties groups2026-09-24No source states: AI company and model, money lost or records, tools it had, company using the AI, sector.
CARBONATO AI-driven botnet hijacks Docker hosts and steals credentials2026-09-24No source states: money lost or records, company using the AI, sector.
OpenAI evaluation agent breached Services Australia Medicare portal and wrote to government database2026-09-24No source states: AI agent used, money lost or records.
LLM pipeline deanonymizes pseudonymous Hacker News and scientist accounts2026-09-24No source states: AI agent used, money lost or records, company using the AI, sector.
SalesBleed: 0-click data exfiltration from Salesforce Agentforce via indirect prompt injection in Web-to-Lead form2026-09-24No source states: money lost or records, company using the AI.
Open-source AI agents breach 27 companies and steal 600,000 card records2026-09-23No source states: money lost or records, company using the AI.
Anthropic model conducted state-sponsored espionage campaign against ~30 targets2026-09-23No source states: AI agent used, money lost or records, tools it had, company using the AI, sector.
Meta Muse zero-day let attackers hijack AI assistant via hidden setting2026-09-22No source states: money lost or records, company using the AI, sector.
EvilTokens AI-assisted device code phishing service disrupted by Microsoft2026-09-22No source states: AI company and model, money lost or records, company using the AI.
Malicious HEIF upload reached OpenAI internal GitHub2026-09-21No source states: AI company and model, money lost or records, tools it had, company using the AI, sector.
Researchers break out of OpenAI Codex sandbox twice2026-09-21No source states: money lost or records, company using the AI.
Frontier LLM agent fabricated a complete calibration-comparison report for commands that never ran2026-09-21No source states: AI company and model, money lost or records, company using the AI.
Zhipu ZCode repository snapshot upload without clear consent2026-09-20No source states: money lost or records, tools it had, company using the AI, sector.
BragJack malicious browser extensions hijack AI agents across five browsers2026-09-19No source states: AI agent used, money lost or records, company using the AI, sector.
Google Gemini accessed systems of three real companies during a misconfigured third-party cybersecurity evaluation2026-09-19No source states: AI agent used, money lost or records, company using the AI, sector.

Previous · Page 6 of 16 · Next