Latest
●Prompt injection turns up in website HTTP headers, study finds●Nezha dashboard can be crashed by any low-privilege member●MCP Python SDK kept sessions forever, letting memory run out●Nginx UI flaws let MCP tools skip config security checks●Bank of America adds 1,000 contractors to fix Mythos-found bugs●UK stops short of AI rules in Cyber Security Bill●GhostAction campaign hits 1,900 GitHub accounts and 30,000 repos●Attackers target critical Langflow flaw in 1,423 exploit attempts
Friday, 16 October 2026
1 agent hack today▼ 7 vs yesterday (8)
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 · 582 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: 47 incidents47JulAug 2026: 83 incidents83AugSep 2026: 146 incidents146SepOct 2026: 57 incidents57OctNov 2026: 0 incidents0NovDec 2026: 0 incidents0Dec
Incidents by sector · 606 total · click a sector to filter
Clear

17 incidents match

Incident dateIncidentVendorSectorAgentRoot causeSeverityStatus
12 Oct 2026CyberXero Uses Claude Code to Steal 628,000+ Ukrainian RecordsAnthropicothercodingtool misuseconfirmed
3 Oct 2026AI-discovered Rejetto HFS auth-bypass flaw exploited in the wildRejettootherotherunknownconfirmed
2 Oct 2026Headroom WebSocket server vulnerable to Cross-Site hijacking (CVE-2026-71416)Headroomotherothermisconfigurationconfirmed
2 Oct 2026A2UI web_core: openUrl permits javascript: URI executionA2UIotherworkflowprompt injectionconfirmed
2 Oct 2026Trigger.dev: Server-side request forgery via webhook alert channelsTrigger.devotherworkflowexcessive permissionsconfirmed
2 Oct 2026Vibe-Trading LLM agent multiple critical vulnerabilitiesVibe-Tradingothercodingexcessive permissionsconfirmed
2 Oct 2026rmcp OAuth client SSRF via server-controlled resource_metadata URLModel Context Protocol (rmcp)otherothermisconfigurationconfirmed
2 Oct 2026Critical RCE Vulnerability Patched in GitLab AI Gateway (Duo Agent Platform)GitLabothercodingexcessive permissionsresolved
2 Oct 2026Trigger.dev CLI debug logs expose resolved environment secretsTrigger.devotherworkflowmisconfigurationconfirmed
1 Oct 2026AI agents attempted to hack US and Canadian government websitesotherotherunknownconfirmed
1 Oct 2026Office-PowerPoint-MCP-Server path traversal via prompt injectionGongRzheothercodingprompt injectionconfirmed
1 Oct 2026vm2 exposes host HTTPS credentials through globalAgentvm2otherotherexcessive permissionsconfirmed
29 Sept 2026AI agent used to breach cybersecurity nonprofit DIVDDIVDotherotherunknownconfirmed
21 Sept 2026Agentic AI attack breaches DIVD via Zammad zero-days, steals volunteer dataZammadotherotherunknownconfirmed
18 Sept 2026AI Agent Used to Breach Spanish Organization, Alter Personal Dataotherotherunknownconfirmed
14 Sept 2026AI agent used in first AI-aided data breach reported in Spainotherothertool misuseconfirmed
13 Aug 2026SiYuan MCP Tool Vulnerabilities in Versions ≤3.8.0SiYuanotherotherprompt injectionconfirmed