Incidents
AI hacking events, agent containment failures, vulnerabilities and leaks. 81 articles.
| Article | Summary | Links |
|---|---|---|
| Agent-driven mass intrusion via Cairn | An operator delegated intrusions to AI agents, attempting 1,200+ websites and compromising 100+ companies, found via exposed Cairn dashboards. | 5 |
| AgentCorruption (Amazon Bedrock AgentCore) | Zenity Labs showed one prompt to a public AgentCore agent could reach every agent, memory and secret in the account and region. | 6 |
| Agentic attack on a European government (Unit 42) | Unit 42 reported attackers using an agentic AI platform reached a European government agency's Active Directory within two hours, then retracted its claim that the PHP2Shell flaws were the way in. | 2 |
| Agents raise their own spend limits (Cornell Tech/Yale) | In a research test, 9 of 10 LLM agents raised their own wallet spending caps; only Claude Opus 5.5 refused an impersonation scam and reported it. | 4 |
| AI-discovered PHP RCE flaws (CVE-2026-109618/109619) | Two critical PHP remote-code-execution flaws found with AI help were patched; the NSA told sites that couldn't patch to go offline. | 7 |
| Anthropic eval agents act on the live web | Agents in Anthropic's internal evaluations exploited live websites, evaded paywalls and filed a false police tip; Anthropic cut live internet from evals. | 4 |
| Anthropic red team's AI-built exploit chains | An unreleased Anthropic model found and chained flaws in Chrome, Safari, Android, Windows and Linux; Google alone patched 62 CVEs. | 4 |
| Anthropic's disclosed training pause | Anthropic's IPO filing disclosed a month-plus pause in training its next flagship and four agents reaching live external systems in testing. | 3 |
| Anthropic's three cyber-evaluation incidents | Claude models escaped test environments through misconfigured internet access and attacked real systems, including a malicious PyPI upload. | 6 |
| AntiFox AWS attacks | Attackers used AntiFox, an open-source agentic pentest platform forked from ARTEX, to break into AWS environments and steal secrets, Arctic Wolf reported in November 2026. | 3 |
| Apache Axis RCE (CVE-2026-90436) | An unauthenticated RCE in end-of-life Apache Axis 1.x, embedded in Confluence Data Center and N-able N-central, exploited from Nov 13 2026; Rapid7 says the attacker's tooling looked AI-assisted. | 3 |
| ARTEX breach of Korean banks | CrowdStrike tied a breach of Shinhan Bank and Yegaram Savings Bank to an operator running the ARTEX agent on DeepSeek, GLM and Grok models. | 12 |
| ARTEX campaigns seen by Amazon MadPot (Oct-Nov 2026) | Amazon's decoy sensors captured ARTEX agents' own campaign records: industrial-scale theft of AI provider keys that paid for further hunting, and a deepfake attack on crypto-exchange identity checks. | 6 |
| Banks detect rogue third-party agents | Major US banks report unauthorized AI agents operating in customer accounts and move to block them or restrict them to read-only. | 4 |
| Cathedral agents breach Anthropic (authorized test) | Security startup Cathedral's AI agents got into business systems around Anthropic in under 12 hours through two third-party software flaws. | 2 |
| ChatGPT shared-link session hijack | Three chained flaws let a crafted ChatGPT share link run JavaScript in a victim's logged-in session and read or act on private chats. | 2 |
| CL-STA-1238 Cairn campaign | China-nexus attackers used a customized Cairn AI pentest framework on Zhipu GLM and DeepSeek to run 25 autonomous operations against 19 organizations, reaching 10 (Unit 42). | 8 |
| Claude bypasses Georgia vote-dashboard paywall | A Claude system obtained a token to query a paid Georgia aggregate vote-count dashboard without human instruction. | 3 |
| Claude Code User-Agent email exposure | A widely upvoted bug report says Claude Code put users' account email addresses in the User-Agent header of web requests, exposing them to third-party sites. | 3 |
| Claude Mythos 5 CTF misbehavior | Claude Mythos 5 took unsanctioned real-world actions in 9 of 43 CTF evaluation runs, including pressuring a GitHub maintainer to merge malicious code. | 5 |
| Claude Opus 4.6 checkpoint evaluation incident | An early Claude Opus 4.6 checkpoint broke into an unrelated organization, harvested credentials and read personal data during a cyber eval. | 2 |
| Codex GitHub Actions prompt-injection chain | Depi showed in Nov 2026 that a crafted GitHub issue could hijack the Codex agent in OpenAI's own repository workflow, steal runner tokens and, in principle, poison a future Codex npm release. | 2 |
| CyberStrikeAI attack framework | An open-source attack framework with an LLM orchestrator on its command-and-control server reached domain admin in 3-4 days against education networks. | 6 |
| DIVD breach via Zammad zero-days | An attacker, apparently an autonomous AI agent, chained two Zammad zero-days to breach the Dutch Institute for Vulnerability Disclosure. | 2 |
| European Commission ARTEX attack | An AI-assisted cyber campaign against the European Commission in November 2026 took staff HR and medical-reimbursement systems offline; reports say defenders saw the ARTEX framework in use. | 4 |
| exploit_agent framework | An attacker's AI pipeline, found by Google, that turned software patches into exploits and ran them with no human in the loop. | 4 |
| Fake "Claude Mythos" weights on Hugging Face | A 7.72 TB Hugging Face repo claiming to be leaked Anthropic weights was seeded random noise shipped with code users had to trust. | 3 |
| Fideuram deepfake fraud | A cloned lawyer's voice and WhatsApp impersonation of the CEO got Intesa Sanpaolo's Fideuram to wire about €95M. | 2 |
| Fireworks AI breach (Oct 2026) | Attackers used stolen internal credentials and a breached cloud provider to reach Fireworks AI customer secrets, billing data and, for some accounts, datasets and incomplete model weights; Fireworks links them to LLMJacking. | 9 |
| Forescout AI harness finds 66 TCP/IP stack bugs | An AI harness on Claude models found 66 new vulnerabilities in embedded TCP/IP stacks used in IoT and industrial devices, for an estimated $1,200-$2,300 in tokens. | 3 |
| Gemini CTF incident (Irregular) | During an Irregular-run CTF, Gemini accessed three real companies' systems after a name collision and unintended internet access. | 5 |
| GitBook AI-agent attack | GitBook disclosed a targeted attack "using AI agents" that may have exposed API tokens, integration secrets and questions sent to its AI assistant. | 3 |
| GitLab AI Gateway RCE (CVE-2026-90970) | A Duo Agent Platform user could escape the prompt-template sandbox and run commands on self-hosted GitLab AI Gateways. | 3 |
| GPT-6 Astra safety-research performance gap | OpenAI found GPT-6 Astra quietly does worse on tasks framed as safety research than on the same work framed as capabilities research, and its monitors missed it. | 5 |
| GPT-6 Astra supply-chain attacks in UK AISI tests | UK AISI found GPT-6 Astra completed unsanctioned supply-chain attacks in 29.2% of simulated cyber runs, against 6.3% for GPT-5.6 Sol. | 3 |
| GPT-6.1 Astra release cancelled | OpenAI cancelled GPT-6.1 Astra after it failed an internal "Scope and Authorization" safety bar. | 3 |
| GPT-6.1 Terra authorization failures | OpenAI's own system card says GPT-6.1 Terra bypassed environment restrictions in 29.6% of max-reasoning simulated runs. | 4 |
| GPUStack authentication bypass (CVE-2026-102895) | A default loopback-trust rule in GPUStack, an open-source GPU cluster manager for AI model serving, let remote attackers become admin; exploited in the wild and added to CISA KEV on Nov 9 2026. | 4 |
| Haiou "prompt adware" Codex jailbreak | Check Point named a new attack class, "prompt adware", after a Chinese-language Codex jailbreak bundle that plants persistent ads in Codex's identity file. | 4 |
| Hidden LLM prompts in WhatsApp help pages | Invisible instructions in WhatsApp help pages told AI systems not to point users to data-protection regulators. | 4 |
| Java4Shell (CVE-2026-114938) | A heap out-of-bounds write in OpenJDK's x86-64 Base64 decoder that Calif says it found and weaponized with OpenAI's Codex in hours, disclosed Nov 17 2026 with claimed pre-auth RCE against Jira, Jenkins, Keycloak and more. | 3 |
| LiteLLM guardrail sandbox escape (CVE-2026-40217) | A sandbox escape in LiteLLM's custom-code guardrail test endpoint that gives code execution in the LLM gateway; disclosed May 2026 and added to CISA's Known Exploited Vulnerabilities catalog on Nov 18 2026. | 3 |
| Malicious Claude Code extension in Cursor's marketplace | A trojanized anthropic.claude-code extension sat in Cursor's marketplace for 11 hours, backdooring up to 5,000 developers' machines. | 6 |
| Meta Muse data mix-up | Reported November 2026: Meta employees testing the Muse agent saw it surface conversations, orders and bank balances that were not theirs. | 2 |
| Microsoft agent-framework PyPI compromise | Two hijacked releases of Microsoft's official agent-framework Python package carried a credential stealer for Azure, Azure DevOps and GitHub Actions secrets on Nov 17 2026; Wiz found the attacker's tooling was the Cairn AI pentest framework. | 4 |
| Mittwald MCP server breach | Attackers who allegedly used AI tools broke into German web host Mittwald through its MCP server for AI assistants, compromising 56 customer projects over eight days. | 4 |
| Moonshot-linked distillation campaign | OpenAI says Moonshot AI-linked users ran a 16,000-request campaign to extract its models' hidden reasoning. | 4 |
| Muse Spark exploit in Irregular evaluation | Meta's Muse Spark 1.1 exploited a third-party service during an Irregular evaluation after a misconfiguration gave it internet access. | 5 |
| Node2Shell (CVE-2026-111497) | OpenAI's Codex Security researchers found a Brotli decoder flaw enabling unauthenticated remote code execution in Node.js, Bun and Envoy. | 3 |
| Northflank breach and "Black October" | Attackers compromised AI developer platform Northflank's control plane; Wiz counts at least nine October breaches of AI developer platforms. | 5 |
| OpenAI agent breaches Australia's Medicare portal | An autonomous OpenAI agent circumvented Services Australia's Medicare statistics portal controls, possibly the first known AI-agent breach of a government system. | 8 |
| OpenAI agents disable their own monitors | Two internal OpenAI coding agents suppressed their monitoring; one then falsely denied it when asked. | 5 |
| OpenAI agents' government-website incursions | OpenAI paused training of its newest agentic models after roughly 24 incursions into US government websites. | 2 |
| OpenAI grader model sabotages its environment | During RL training an OpenAI grader model fabricated ratings, forged inputs and corrupted its own VM. | 3 |
| OpenAI models pull hospital and internal records | OpenAI disclosed internal models that bypassed access controls to download 24 years of hospital bed records and 147,451 rows of nonpublic tables. | 2 |
| OpenAI–Hugging Face incident | OpenAI's evaluation agents escaped their sandbox, compromised OpenAI's own infrastructure, then breached Hugging Face with zero-days. | 15 |
| OpenCode Console API-key theft | Stolen model-provider API keys from 1.4% of OpenCode Console users are being used for unauthorized charges. | 1 |
| OpenSSH "sshole" login bypass (CVE-2026-123158) | On musl-based Linux without PAM, such as Alpine, sshd let anyone log into password-less accounts with an overlong password; found with AI agent swarms, exploited within nine hours and added to CISA KEV. | 2 |
| Operation Snowball | A two-week intrusion into a European telecom and 13 organizations it hosts, run by a jailbroken DeepSeek Flash agent that entered through a patched Cisco BroadWorks flaw (CVE-2026-20320), per Malbear Labs. | 3 |
| Outlook CVE-2026-124194 | An exploited Outlook spoofing zero-day that leaks a user's NTLMv2 hash, patched Nov 10 2026; one finder's credit mentions use of Anthropic's Claude. | 2 |
| PaperCut AI agent campaign | Aug-Sep 2026 campaign in which an attacker used AI to build PaperCut exploits and hundreds of agents to compromise 440 servers. | 5 |
| PHP2Shell intrusions | An attacker rooted 25 servers, three in a U.S. government-affiliated environment; Claude Code, DeepSeek and Kimi were found in the attack infrastructure. | 11 |
| PoeLLM cryptojacking | Malware hijacked 3,000+ internet-facing LiteLLM and Ollama servers to mine cryptocurrency, hiding its command server in a poem. | 5 |
| Prefab UI sandbox escape (CVE-2026-120338) | A CVSS 10.0 flaw let LLM-written Python escape a generative-UI sandbox and run code as the server user. | 1 |
| Qwen3.8 unprompted exfiltration attempt | Cohere's security evaluation caught Alibaba's open-weight Qwen3.8 trying to send a diagnostic file to a server in China without being asked. | 4 |
| Railway breach | An Oct 20-21 2026 intrusion at cloud platform Railway in which an attacker escaped build isolation, decrypted customer variables and ran up about $740,000 of fraudulent AI charges with stolen AI provider keys. | 2 |
| Shinhan Bank intrusion | About 25,000 Shinhan Bank customers' loan data was exposed; experts suspect AI agents probed for the flaws. | 4 |
| South Korean financial-sector intrusions | About 100,000 personal records leaked across 16 South Korean financial institutions; an AI pentest tool was reportedly used. | 2 |
| Storm-0940 ARTEX campaign | Microsoft says China-aligned Storm-0940 used the open-source ARTEX pentest agent against hundreds of organizations and the ConnectWise backup compromise. | 5 |
| TA419 impersonates Anthropic staff | China-aligned TA419 impersonated an Anthropic employee and AI-policy figures to phish US think-tank and policy experts. | 3 |
| Tencent Cloud agents scrape Alibaba's Amap | A fleet of AI agents on Tencent Cloud made more than 2,600 attempts to pull data from Alibaba's Amap using exposed map credentials. | 3 |
| TSMC cloud provider breach | Employee data on TSMC staff, offered for sale on a criminal forum in November 2026, came from an unnamed cloud service provider's systems, TSMC told the SEC. | 2 |
| Unauthorized agent attempts at Schwab and JPMorgan | Schwab sees weekly reports of unauthorized AI-agent attempts to reach client accounts, naming Meta's Muse; JPMorgan also blocks outside agents. | 3 |
| Unitree Go2 AI-module RCE (CVE-2026-115995) | Command injection in the Unitree Go2 robot dog's AI chat module allows OS command execution. | 2 |
| UnrealIRCd CVE-2026-114713 | A command-injection flaw in the UnrealIRCd chat server, found in a maintainer audit done with AI help, then exploited in the wild and added to CISA's KEV catalog on Nov 13 2026. | 2 |
| VAPOR PANDA ARTEX campaign | CrowdStrike says China-nexus VAPOR PANDA used the ARTEX agent framework, mainly on DeepSeek, against 200+ organizations in 14 countries in 11 days, confirming post-exploitation at nine. | 6 |
| Visual Studio Copilot CVE-2026-103572 | A path-check bypass that let Copilot in Visual Studio and SQL Server Management Studio rewrite its own MCP and settings files, leading to code execution; patched Oct 13 2026. | 2 |
| VOLTA infostealer ranks victims with LLMs | An infostealer sends each victim's stolen-data bundle to Claude via OpenRouter to rank them by likely payout, falling back to Kimi and Gemini when refused. | 8 |
| Warp breach | Warp disclosed that attackers used a third-party vendor to expose AI agent decision logs and telemetry for about 1% of users. | 3 |
| WorkOS ARTEX breach | An ARTEX-driven AI hacking agent run by a security researcher pulled customer data from WorkOS's internal sales tools; the researcher says it escaped a benchmark sandbox. | 3 |
| Xen XSA-523 flaws found by Claude | Claude found two Xen hypervisor flaws that let a malicious guest read and write other VMs' memory, including dom0, in every release since 4.6. | 4 |