Latest
●Fake job interview preceded $6.3bn Binance crypto theft●WorkOS says attacker used ARTEX AI to breach sales app●Think tank warns of self-sustaining 'sovereign agents'●Path traversal in Praktor lets Telegram users plant agent orders●Stolen cloud keys fuel a resale market for LLM access●CrowdStrike to Buy AI Security Firms Fiddler and Dreadnode●NCSC warns AI-powered ransomware will hit UK infrastructure by 2028●Chinese hackers used open-source ARTEX AI to attack 200 organisations
Wednesday, 4 November 2026
0 agent hacks today▼ 4 vs yesterday (4)
The Agentic TimesPowered byVortal

Incident database

Structured records of AI agent security incidents: what happened, which vendor and agent type, the root cause, and every source we used. Filter, browse, or download as CSV.

Incidents by month, 2026 · 663 total · click a month to filter
Jan 2026: 23 incidents23JanFeb 2026: 26 incidents26FebMar 2026: 46 incidents46MarApr 2026: 47 incidents47AprMay 2026: 53 incidents53MayJun 2026: 55 incidents55JunJul 2026: 49 incidents49JulAug 2026: 83 incidents83AugSep 2026: 150 incidents150SepOct 2026: 125 incidents125OctNov 2026: 6 incidents6NovDec 2026: 0 incidents0Dec
Incidents by sector · 690 total · click a sector to filter

Highlighted: incidents recorded on 4 November 2026, shown in place among all incidents.Clear

690 incidents

Incident dateIncidentVendorSectorAgentRoot causeSeverityStatus
3 Nov 2026Praktor path traversal allows instruction injection via Telegram uploadsmtzanidakistechnologyworkflowprompt injectionresolved
3 Nov 2026WorkOS breach: attacker used ARTEX AI to access sales app dataWorkOStechnologyotherunknownconfirmed
3 Nov 2026LLMjacking: Stolen Cloud Credentials Used to Resell LLM Accesstechnologyothermisconfigurationconfirmed
2 Nov 2026VOLTA Infostealer Abuses Claude, Gemini, Kimi AI to Rank Stolen Datatechnologyothertool misuseconfirmed
2 Nov 2026Chinese hackers use ARTEX AI framework in attacks on 200 orgstechnologycodingtool misuseconfirmed
1 Nov 2026Trigger.dev discloses theft of customer environment variablesTrigger.devtechnologyworkflowdata leakconfirmed
31 Oct 2026Chainalysis discloses data breach via offensive agentic techniquesChainalysisfinanceothertool misuseconfirmed
31 Oct 2026Northflank breach leads to abuse of customers' AI API keysNorthflanktechnologyotherdata leakconfirmed
30 Oct 2026Chinese State Hackers Use AI Tool ARTEX to Target 200+ Organizationstechnologyothertool misuseconfirmed
30 Oct 2026"Black October": Agentic Attacks Fuel LLMJacking Wavetechnologycodingsupply chainconfirmed
29 Oct 2026Embedded-browser flaws found in five AI coding tools, two remain unpatchedOpenAI, Microsoft, Cursor, GitHub, Anthropictechnologycodingexcessive permissionsconfirmed
29 Oct 2026Hugging Face crypto-mining malware campaign resurfaces, targets AI coding agentsHugging Facetechnologycodingsupply chainconfirmed
29 Oct 2026CVE-2026-119050: Agno PandasTools unsafe reflection vulnerabilityAgnotechnologyotherprompt injectionconfirmed
29 Oct 2026North Korean hackers steal $6.3B from Binance via fake job interviewBinancefinanceothersupply chainconfirmed
29 Oct 2026Shadowy relay service disables sandboxes in OpenAI Codex, Claude CodeOpenAI/Anthropictechnologycodingmisconfigurationconfirmed
29 Oct 2026Malicious Claude Code-branded extension backdoors Cursor users via SSHCursortechnologycodingsupply chainconfirmed
29 Oct 2026@sylphx/pdf-reader-mcp HTTP transport accepts unauthenticated requestssylphxtechnologyothermisconfigurationconfirmed
28 Oct 2026Mem0 Cross-Tenant Conversation Leak via Delimiter CollisionMem0technologyotherprompt injectionconfirmed
28 Oct 2026Threat Actor Impersonates AI Bots to Scan for Exposed Credentialstechnologybrowsingunknownconfirmed
28 Oct 2026CVE-2026-59176: Functype MCP Server Arbitrary Code ExecutionFunctypetechnologyothertool misuseconfirmed
27 Oct 2026Warp breach exposes AI agent logs and user telemetry dataWarptechnologycodingsupply chainconfirmed
27 Oct 2026Flexible GraphRAG Cypher Injection via Broken String EscapingFlexible GraphRAGtechnologyotherprompt injectionconfirmed
27 Oct 2026AI agent finds four severe flaws in EPICS industrial control softwareEPICS Collaborationenergyotherunknownresolved
27 Oct 2026'Aokigahara' Infostealer Targets AI Assistant Sessions and Developer Keyringstechnologyotherdata leakconfirmed
27 Oct 2026MLflow CrewAI autologging leaks LLM API keys in trace spansMLflowtechnologycodingdata leakconfirmed
27 Oct 2026AI-Driven 'CyberStrikeAI' Used in Automated Attacks on Japanese Organizationsotherothertool misuseconfirmed
27 Oct 2026Strands Agents: Default FileSessionManager storage vulnerabilitiesStrandstechnologyothermisconfigurationconfirmed
26 Oct 2026npm worm hijacked GitHub accounts, armed 42 repos with hidden payloadtechnologycodingsupply chainconfirmed
26 Oct 2026AI Model 'Mythos 5' Created Fake Identities, Submitted Malicious Codetechnologycodingtool misuseconfirmed
26 Oct 2026Alibaba's Qwen3.8-Flash-Next tried to contact server in China during testAlibabatechnologycodingunknownconfirmed
26 Oct 2026Malicious Downloads file tries to trick AI coding agent into installing malwareForever Securitytechnologycodingprompt injectionconfirmed
26 Oct 2026In-the-Wild Prompt Injection Attack Exploits AI Coding Agents via Markdowntechnologycodingprompt injectionconfirmed
25 Oct 2026AI-Assisted Hackers Exploit PHP2Shell Flaws, Breach EU Government Entitygovernmentothertool misuseconfirmed
25 Oct 2026OpenAI AI Agents Found Capable of VM Escapes, Secret Cross-Sandbox CommunicationOpenAItechnologyothertool misuseconfirmed
25 Oct 2026Malicious AGENTS.md file hijacks AI coding agents into installing rogue npm packagetechnologycodingprompt injectionconfirmed
25 Oct 2026Gheist campaign abuses stolen GitHub tokens to plant secret-stealing workflowsGitHubtechnologyworkflowsupply chainconfirmed
23 Oct 2026China-linked APT Uses AI Pentest Tool Artex in ConnectWise AttacksConnectWisetechnologyothertool misuseconfirmed
23 Oct 2026AI-generated attacks compromise 105 sites, gain full domain controltechnologyothertool misuseconfirmed
23 Oct 2026Fallow Path Traversal Vulnerability in Jest/Vitest Config ParsingFallowtechnologyothertool misuseresolved
23 Oct 2026FastMCP OAuth credential binding vulnerability in versions 4.0.0-4.1.1FastMCPtechnologyothermisconfigurationconfirmed
23 Oct 2026MLflow SSRF vulnerability on unauthenticated scorer endpointsMLflowtechnologyotherprompt injectionconfirmed
23 Oct 2026Banks report detecting rogue AI agents acting unexpectedlyfinanceotherunknownconfirmed
23 Oct 2026LangGraph namespace labels bypass allows cross-tenant data accessLangChaintechnologyworkflowexcessive permissionsconfirmed
23 Oct 2026vLLM DoS via unvalidated multimodal processor argumentsvLLMtechnologyotherexcessive permissionsconfirmed
23 Oct 2026Ransomware Affiliates Used AI Agent Framework 'Phantom' for Intrusionstechnologyothertool misuseconfirmed
23 Oct 2026FastMCP Authorization Bypass via Direct Component CallsPrefectHQtechnologyotherexcessive permissionsconfirmed
22 Oct 2026Storm-0940-linked actor uses AI agent 'ARTEX' to target IT/software vendorstechnologyothertool misuseconfirmed
22 Oct 2026OpenCode Flaw Allowed Malicious MCP Servers to Run Code at Sign-InAnomalytechnologycodingsupply chainresolved
22 Oct 2026Critical flaw in x402 SDK could drain AI agents' token balancesx402technologyworkflowmisconfigurationresolved
21 Oct 2026CVE-2026-114107: Vibe-Trading Indirect Prompt Injection RCEHKUDStechnologyotherprompt injectionconfirmed