AI Threat Alert

AI Security Threat Feed

Latest CVEs affecting AI/ML systems — LLM frameworks, ML libraries, AI agents, vector databases, and inference servers. Vulnerabilities are tracked from NVD, GitHub Advisory, CISA KEV, MITRE ATLAS, and enriched with CVSS, EPSS, exploitation confidence, AI-component classification, and compliance mappings to ISO 42001, EU AI Act, NIST AI RMF, and OWASP LLM Top 10. Updated continuously as new CVEs are published.

Sources
Each CVE is enriched with
  • CVSS severity
  • EPSS exploit probability
  • Exploitation confidence
  • AI-component classification
  • Compliance mappings
4,307

AI/ML CVEs Tracked

533

Critical

95

New This Week

25

In CISA KEV

Sort:DateCVSSEPSSKEV firstMost exploited
Filter:AllCriticalHighMediumKEV onlyActive exploitationHas patchNo patch

Latest AI Security Threats

Showing 20 of 1431 results — has patch
LOWEXPLOIT AVAIL

Open WebUI: IDOR leaks private channel/DM threads

CVE-2026-59215
3.1
EPSS 0.3%
Auth BypassData LeakageFramework
open-webuiPatch: 0.10.0CWE-63921 ATLAS
LOWEXPLOIT AVAIL

Open WebUI: cache leak exposes cross-user model lists

CVE-2026-59213
3.5
EPSS 0.4%
Data LeakagePrivacy ViolationAPIInference
open-webuiPatch: 0.10.0CWE-52421 ATLAS
MEDIUMEXPLOIT AVAIL

Open WebUI: read-only users can inject files into RAG KBs

CVE-2026-59217
4.3
EPSS 0.4%
Auth BypassPrompt InjectionRAGAPI
open-webuiPatch: 0.10.0CWE-86222 ATLAS
HIGHEXPLOIT AVAIL

Open WebUI: session hijack enables cross-user code exec

CVE-2026-59216
7.7
EPSS 0.5%
Auth BypassCode ExecutionPrivacy ViolationAgentPlugin
open-webuiPatch: 0.10.0CWE-9424 ATLAS
HIGHEXPLOIT AVAIL

Open WebUI: revoked JWTs bypass WebSocket auth

CVE-2026-59219
7.1
EPSS 0.6%
Auth BypassData LeakageFrameworkAPI
open-webuiPatch: 0.10.0CWE-61322 ATLAS
MEDIUM

n8n: multi-issuer JWT sub collision bypasses auth

CVE-2026-59208
6.8
EPSS 0.3%
Auth BypassPrivacy ViolationAgent
n8nPatch: 2.28.1CWE-287164 ATLAS
MEDIUM

n8n: MCP tool bypasses credential domain allowlist

CVE-2026-59207
6.5
EPSS 0.4%
Auth BypassData LeakageAgentPlugin
n8nPatch: 2.28.1CWE-693163 ATLAS
HIGH

n8n: prototype pollution lets guests hit admin APIs

CVE-2026-59206
7.1
EPSS 0.7%
Auth BypassPrivacy ViolationAgentFrameworkAPI
n8nPatch: 1.123.61CWE-1321162 ATLAS
LOWEXPLOIT AVAIL

Open WebUI: unauth Socket.IO bypass alters doc state

CVE-2026-59715
3.1
EPSS 0.4%
Auth BypassFramework
open-webuiPatch: 0.10.0CWE-30621 ATLAS
MEDIUMEXPLOIT AVAIL

Open WebUI: ReDoS in skill mentions blocks event loop

CVE-2026-59220
6.5
EPSS 0.6%
DoSFrameworkPlugin
open-webuiPatch: 0.10.0CWE-133322 ATLAS
LOW

Open WebUI: deactivated users retain automation access

CVE-2026-59226
3.1
EPSS 0.5%
Auth BypassAgentModel
open-webuiPatch: 0.10.0CWE-28521 ATLAS
MEDIUMEXPLOIT AVAIL

Open WebUI: image-edit API bypasses admin permission gate

CVE-2026-59227
4.3
EPSS 0.4%
Auth BypassAPIPlugin
open-webuiPatch: 0.10.0CWE-86223 ATLAS
MEDIUM

Open WebUI: timing leak enables account enumeration

CVE-2026-59218
5.3
EPSS 0.4%
Privacy ViolationAuth BypassFramework
open-webuiPatch: 0.10.0CWE-20821 ATLAS
HIGH

Open WebUI: Pyodide sandbox bypass reaches admin RCE

CVE-2026-59214
7.3
EPSS 0.4%
Code ExecutionAuth BypassData LeakageFrameworkAgentPlugin
open-webuiPatch: 0.10.0CWE-7923 ATLAS
HIGHEXPLOIT AVAIL

Cline: missing Origin check on Hub enables RCE

CVE-2026-59723
8.8
EPSS 0.2%
Auth BypassCode ExecutionAgentPlugin
clinePatch: 3.0.30CWE-34625 ATLAS
HIGHEXPLOIT AVAIL

Serena: unauth dashboard API enables RCE via memory poisoning

CVE-2026-49471
8.3
EPSS 0.4%
Auth BypassPrompt InjectionCode ExecutionAgentAPI
serena-agentPatch: 1.5.2CWE-3066 ATLAS
HIGHKEV

LiteLLM: MCP auth bypass via fabricated OAuth header

CVE-2026-59822
8.2
EPSS 0.8%
Auth BypassAPIAgentPlugin
litellmPatch: 1.84.0CWE-28763 ATLAS
HIGH

LiteLLM: code exec via unsandboxed Custom Guardrails

CVE-2026-59821
7.2
EPSS 0.9%
Code ExecutionData LeakageFrameworkAPIPlugin
litellmPatch: 1.82.0CWE-9463 ATLAS
MEDIUM

LiteLLM: Zip Slip in Skills upload allows file write

CVE-2026-59820
6.5
EPSS 0.6%
Code ExecutionAPIPlugin
litellmPatch: 1.83.7CWE-2263 ATLAS
MEDIUM

LiteLLM: admin-scope local file read via OIDC ref

CVE-2026-59819
4.9
EPSS 0.6%
Data LeakageData ExtractionAPIFramework
litellmPatch: 1.83.10CWE-7362 ATLAS

Frequently asked questions

What is an AI security threat feed?

An AI security threat feed is a continuously updated stream of vulnerabilities (CVEs) affecting AI and machine-learning systems — LLM frameworks, ML libraries, AI agents, vector databases, and inference servers — filtered out of the broader CVE firehose and enriched for relevance.

Which sources are the AI CVEs tracked from?

CVEs are tracked from NVD, GitHub Advisory, CISA KEV, and MITRE ATLAS, then enriched with CVSS, EPSS, exploitation confidence, AI-component classification, and compliance mappings.

What AI systems do these vulnerabilities affect?

Coverage spans LLM frameworks, ML libraries, AI agents, vector databases, and inference servers — the components most security teams now run in production.

How often is the AI threat feed updated?

The feed updates continuously as new CVEs are published and enriched, so the most recent AI/ML vulnerabilities appear at the top.

Is the AI security feed free?

Yes — the public feed is free to browse. A Pro subscription adds breaking alerts, MITRE ATLAS mappings, compliance reports (ISO 42001, EU AI Act), and full CISO analysis.

Need deeper analysis?

Get ATLAS technique mappings, compliance reports (ISO 42001, EU AI Act), breaking alerts, and full CISO analysis with a Pro subscription.

Start 14-Day Free Trial