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

96

New This Week

25

In CISA KEV

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

Latest AI Security Threats

Showing 20 of 616 results — High severity, has patch
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
HIGH

n8n: SQL injection via MySQL v1 node expressions

CVE-2026-59257
8.8
EPSS 0.6%
Code ExecutionData LeakageAgentPlugin
n8nPatch: 1.123.61CWE-89163 ATLAS
HIGHEXPLOIT AVAIL

Open WebUI: stored XSS via chat 'embeds' iframe escape

CVE-2026-26193
7.3
EPSS 0.2%
Code ExecutionAuth BypassData LeakageFramework
open-webuiPatch: 0.6.44CWE-7922 ATLAS
HIGHEXPLOIT AVAIL

Open WebUI: stored XSS via citation iFrame → admin RCE

CVE-2026-26192
7.3
EPSS 0.2%
Code ExecutionData LeakageSocial EngineeringFrameworkRAG
open-webuiPatch: 0.7.0CWE-7924 ATLAS
HIGHEXPLOIT AVAIL

Open WebUI: chat XSS steals tokens, admin RCE

CVE-2025-46719
--
EPSS 0.6%
Code ExecutionAuth BypassData LeakageFrameworkPlugin
open-webuiPatch: 0.6.6CWE-7924 ATLAS
HIGHEXPLOIT AVAIL

vLLM: crafted spec-decoding request crashes GPU worker (DoS)

CVE-2026-54234
7.5
EPSS 0.6%
DoSInference
vllmPatch: 0.24.0CWE-20942 ATLAS
HIGH

Coder AI Bridge Proxy: TLS bypass leaks BYOK keys

CVE-2026-55436
7.4
EPSS 0.3%
Data LeakageAuth BypassAPIAgent
github.com/coder/coder/v2Patch: 2.34.2CWE-2956.3K2 ATLAS
HIGH

Coder: session token leak via workspace app URL

CVE-2026-55431
7.7
EPSS 0.3%
Auth BypassData LeakageSupply ChainAgentPlugin
github.com/coder/coder/v2Patch: 2.34.2CWE-5226.3K4 ATLAS
HIGH

Coder: agent IP spoofing hijacks workspace traffic

CVE-2026-55428
8.2
EPSS 0.4%
Auth BypassPrivacy ViolationAgent
github.com/coder/coder/v2Patch: 2.34.2CWE-2856.3K
HIGH

Coder: cross-workspace agent hijack via app ID reuse

CVE-2026-55429
8.7
EPSS 0.5%
Auth BypassPrivacy ViolationAgentAPI
github.com/coder/coder/v2Patch: 2.34.2CWE-6396.3K1 ATLAS
HIGH

Coder: SSH config injection via config-ssh enables RCE

CVE-2026-55427
8.3
EPSS 0.5%
Code ExecutionSupply ChainAgent
github.com/coder/coder/v2Patch: 2.34.2CWE-746.3K2 ATLAS
HIGH

Coder: user-admin can hijack owner accounts

CVE-2026-55077
7.2
EPSS 0.6%
Auth BypassCode ExecutionAgent
github.com/coder/coder/v2Patch: 2.34.2CWE-2856.3K2 ATLAS
HIGH

Coder: OIDC auth bypass enables account takeover

CVE-2026-55075
7.4
EPSS 0.5%
Auth BypassPrivacy ViolationAgentTraining Data
github.com/coder/coder/v2Patch: 2.34.2CWE-2876.3K3 ATLAS
HIGH

Coder: OIDC type-confusion enables account takeover

CVE-2026-55076
7.4
EPSS 0.6%
Auth BypassAgentAPI
github.com/coder/coder/v2Patch: 2.34.2CWE-2876.3K3 ATLAS
HIGHEXPLOIT AVAIL

Langroid: auth bypass invokes disabled tools via raw JSON

CVE-2026-54771
8.1
EPSS 0.4%
Auth BypassCode ExecutionAgentFramework
langroidPatch: 0.65.3CWE-7443 ATLAS
HIGH

Camel: input validation flaw in LLM agent tool components

CVE-2026-49042
7.3
EPSS 0.7%
Data LeakageDoSAgentFramework
org.apache.camel:camel-spring-ai-toolsPatch: 4.18.3CWE-203.2K2 ATLAS
HIGHEXPLOIT AVAIL

langroid: SQL blocklist bypass leaks Postgres files

CVE-2026-50180
--
EPSS 0.7%
Prompt InjectionData ExtractionAuth BypassAgentFramework
langroidPatch: 0.64.0CWE-2244 ATLAS
HIGHEXPLOIT AVAIL

Langroid: path traversal escapes sandboxed file tools

CVE-2026-50181
7.1
EPSS 0.2%
Auth BypassData LeakageAgentFramework
langroidPatch: 0.64.0CWE-2244 ATLAS
HIGH

OpenClaw: owner-command auth bypass via native cmds

GHSA-p73f-w79w-jqr5
--
Auth BypassCode ExecutionAgentPlugin
openclawPatch: 2026.5.6CWE-86333 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