Latest
●MLflow autologging writes CrewAI API keys into trace data●AI agent finds four severe flaws in EPICS control software●Researchers say 44 AI agents drove attacks on Japanese targets●New 'Aokigahara' stealer goes after AI assistant sessions●Warp discloses breach exposing AI agent logs and telemetry●Strands Agents leaves agent session files open to local attackers●Broken escape function lets documents wipe GraphRAG databases●Three MCP servers let agents be tricked into running shell commands
Wednesday, 28 October 2026
1 agent hack today▼ 9 vs yesterday (10)
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 · 637 total · click a month to filter
Jan 2026: 23 incidents23JanFeb 2026: 26 incidents26FebMar 2026: 46 incidents46MarApr 2026: 47 incidents47AprMay 2026: 53 incidents53MayJun 2026: 54 incidents54JunJul 2026: 48 incidents48JulAug 2026: 83 incidents83AugSep 2026: 147 incidents147SepOct 2026: 110 incidents110OctNov 2026: 0 incidents0NovDec 2026: 0 incidents0Dec
Incidents by sector · 663 total · click a sector to filter

Highlighted: incidents recorded on 28 October 2026, shown in place among all incidents.Clear

663 incidents

Incident dateIncidentVendorSectorAgentRoot causeSeverityStatus
27 Oct 2026Flexible GraphRAG Cypher Injection via Broken String EscapingFlexible GraphRAGtechnologyotherprompt injectionconfirmed
27 Oct 2026Strands Agents: Default FileSessionManager storage vulnerabilitiesStrandstechnologyothermisconfigurationconfirmed
27 Oct 2026'Aokigahara' Infostealer Targets AI Assistant Sessions and Developer Keyringstechnologyotherdata leakconfirmed
27 Oct 2026AI-Driven 'CyberStrikeAI' Used in Automated Attacks on Japanese Organizationsotherothertool misuseconfirmed
27 Oct 2026MLflow CrewAI autologging leaks LLM API keys in trace spansMLflowtechnologycodingdata leakconfirmed
27 Oct 2026Warp breach exposes AI agent logs and user telemetry dataWarptechnologycodingsupply chainconfirmed
27 Oct 2026AI agent finds four severe flaws in EPICS industrial control softwareEPICS Collaborationenergyotherunknownresolved
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 2026In-the-Wild Prompt Injection Attack Exploits AI Coding Agents via Markdowntechnologycodingprompt injectionconfirmed
26 Oct 2026Malicious Downloads file tries to trick AI coding agent into installing malwareForever Securitytechnologycodingprompt injectionconfirmed
26 Oct 2026Alibaba's Qwen3.8-Flash-Next tried to contact server in China during testAlibabatechnologycodingunknownconfirmed
25 Oct 2026Gheist campaign abuses stolen GitHub tokens to plant secret-stealing workflowsGitHubtechnologyworkflowsupply chainconfirmed
25 Oct 2026Malicious AGENTS.md file hijacks AI coding agents into installing rogue npm packagetechnologycodingprompt 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
23 Oct 2026Fallow Path Traversal Vulnerability in Jest/Vitest Config ParsingFallowtechnologyothertool misuseresolved
23 Oct 2026AI-generated attacks compromise 105 sites, gain full domain controltechnologyothertool misuseconfirmed
23 Oct 2026Banks report detecting rogue AI agents acting unexpectedlyfinanceotherunknownconfirmed
23 Oct 2026vLLM DoS via unvalidated multimodal processor argumentsvLLMtechnologyotherexcessive permissionsconfirmed
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 2026Ransomware Affiliates Used AI Agent Framework 'Phantom' for Intrusionstechnologyothertool misuseconfirmed
23 Oct 2026LangGraph namespace labels bypass allows cross-tenant data accessLangChaintechnologyworkflowexcessive permissionsconfirmed
23 Oct 2026China-linked APT Uses AI Pentest Tool Artex in ConnectWise AttacksConnectWisetechnologyothertool misuseconfirmed
23 Oct 2026FastMCP Authorization Bypass via Direct Component CallsPrefectHQtechnologyotherexcessive permissionsconfirmed
22 Oct 2026Critical flaw in x402 SDK could drain AI agents' token balancesx402technologyworkflowmisconfigurationresolved
22 Oct 2026OpenCode Flaw Allowed Malicious MCP Servers to Run Code at Sign-InAnomalytechnologycodingsupply chainresolved
22 Oct 2026Storm-0940-linked actor uses AI agent 'ARTEX' to target IT/software vendorstechnologyothertool misuseconfirmed
21 Oct 2026Threat Actor Used AI to Plan Credential Theft and Other Cybercrimetechnologyothertool misuseconfirmed
21 Oct 2026Chinese AI model writes more hackable code for US defense taskstechnologycodingunknownconfirmed
21 Oct 2026Malicious LiteLLM Package Version Delivers Credential Stealer, BackdoorLiteLLMtechnologyothersupply chainconfirmed
21 Oct 2026CVE-2026-114107: Vibe-Trading Indirect Prompt Injection RCEHKUDStechnologyotherprompt injectionconfirmed
21 Oct 2026LiteLLM supply chain attack distributes credential-stealing malwareBerriAItechnologyothersupply chainconfirmed
21 Oct 2026djust: Arbitrary absolute-path file read in MCP tooldjusttechnologyotherexcessive permissionsconfirmed
20 Oct 2026LangAlpha indirect prompt injection allows remote code executionginlix-aitechnologycodingprompt injectionconfirmed
20 Oct 2026Phishing Campaign Hijacks Cloud Billing Accounts for LLM API Abusetechnologyotherunknownconfirmed
20 Oct 2026Hackers abuse AI pen-test tool Cairn to breach hundreds of sitesmanufacturingothertool misuseconfirmed
20 Oct 2026A2A Java SDK credentials leaked via HTTP redirectA2A Projecttechnologyotherexcessive permissionsconfirmed
20 Oct 2026AI Agents Used to Autonomously Breach Over 100 Companies' Websitesotherothertool misuseconfirmed
20 Oct 2026AI Platform Cairn Abused to Hack Over 100 OrganizationsCairntechnologyothertool misuseconfirmed
19 Oct 2026Fake Web3 Accelerator Spreads Malware via npm, Hijacks AI Agent Traffictechnologycodingsupply chainconfirmed
19 Oct 2026AI Gateway MCP session hijacking vulnerability with default insecure seedEnvoytechnologyothermisconfigurationconfirmed
19 Oct 2026CVE-2026-112308: crewai-tools SSRF in SeleniumScrapingToolcrewAItechnologyotherprompt injectionconfirmed
19 Oct 2026russh: Unbounded memory allocation in SSH agent via crafted constraintsrusshtechnologyotherexcessive permissionsconfirmed
18 Oct 2026WhatsApp Help Pages Had Hidden Instructions Steering AI Chatbot Away From RegulatorsWhatsApptechnologycustomer serviceprompt injectionresolved
16 Oct 2026CVE-2026-95183: Prompt Injection in DeepSeek Harness Context CompactionDeepSeektechnologyotherprompt injectionconfirmed
16 Oct 2026Fake Claude and ChatGPT campaigns use ClickFix tactics against developerstechnologyotherunknownconfirmed
16 Oct 2026OpenCode Console breach may have exposed AI provider API keysOpenCodetechnologycodingunknownconfirmed
16 Oct 2026OpenAI Model Hacked Data Portals and Took Crypto to Complete TaskOpenAItechnologycodingtool misuseconfirmed