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 1527 results — Medium severity
MEDIUM

vLLM: malformed prompt embeds crash serving via M-RoPE

CVE-2026-55514
6.5
EPSS 0.7%
DoSInferenceModel
vllmPatch: 0.24.0CWE-617943 ATLAS
MEDIUMEXPLOIT AVAIL

Coder: CORS bypass via workspace subdomain proxy

CVE-2026-55438
5.8
EPSS 0.2%
Auth BypassData LeakageTraining DataAPI
github.com/coder/coder/v2Patch: 2.34.2CWE-3466.3K2 ATLAS
MEDIUM

Coder: stored XSS in agent logs risks admin session

CVE-2026-55437
5.4
EPSS 0.3%
Social EngineeringData LeakageAgent
github.com/coder/coder/v2Patch: 2.34.2CWE-796.3K2 ATLAS
MEDIUM

Coder AI Bridge: suspended user auth bypass

CVE-2026-55435
5.4
EPSS 0.3%
Auth BypassAPIAgent
github.com/coder/coder/v2Patch: 2.34.2CWE-8636.3K4 ATLAS
MEDIUM

Coder: AI Bridge unbounded read enables DoS

CVE-2026-55434
6.5
EPSS 0.6%
DoSAPI
github.com/coder/coder/v2Patch: 2.34.2CWE-7706.3K2 ATLAS
MEDIUM

Coder: missing ActionUpdate check allows devcontainer wipe

CVE-2026-55433
5.4
EPSS 0.4%
Auth BypassDoSAgentFramework
github.com/coder/coder/v2Patch: 2.34.2CWE-8626.3K3 ATLAS
MEDIUM

Coder: sub-agent apps bypass org port-sharing policy

CVE-2026-55432
5.4
EPSS 0.3%
Auth BypassAgent
github.com/coder/coder/v2Patch: 2.34.2CWE-8626.3K1 ATLAS
MEDIUM

Coder: zip decompression bomb crashes coderd (DoS)

CVE-2026-55078
6.5
EPSS 0.6%
DoSAPI
github.com/coder/coder/v2Patch: 2.34.2CWE-4096.3K2 ATLAS
MEDIUM

Coder: X-Forwarded-Host spoof leaks victim app data

CVE-2026-55430
5.8
EPSS 0.2%
Auth BypassPrivacy ViolationAgentAPI
github.com/coder/coder/v2Patch: 2.34.2CWE-3456.3K2 ATLAS
MEDIUM

Coder: unbounded FileSize crashes coderd via OOM

CVE-2026-55079
4.9
EPSS 0.6%
DoSAgent
github.com/coder/coder/v2Patch: 2.34.2CWE-7896.3K
MEDIUMEXPLOIT AVAIL

vLLM: audio upload OOMs process before size check

CVE-2026-55646
6.5
EPSS 0.5%
DoSInferenceAPI
vllmPatch: 0.24.0CWE-400942 ATLAS
MEDIUM

OpenAI Codex: prompt injection exfils data via images

CVE-2026-14898
6.5
EPSS 0.4%
Prompt InjectionData LeakageAgentAPI
4 ATLAS
MEDIUM

OP-TEE: off-by-one in SHA-3 CE overflows TEE kernel heap

CVE-2026-40257
5.5
EPSS 0.2%
DoSCode ExecutionInferenceModel
CWE-7871 ATLAS
MEDIUM

LangSmith SDK: arbitrary file read via TracingMiddleware

CVE-2026-59152
5.0
EPSS 0.2%
Data LeakageAuth BypassFrameworkAgent
langsmith-sdk3.2K3 ATLAS
MEDIUMEXPLOIT AVAIL

ONNX: OOB read in shape inference parsing untrusted models

CVE-2026-14647
4.3
EPSS 0.4%
Code ExecutionDoSModelFramework
onnxCWE-1191.1K2 ATLAS
MEDIUM

Mautic Focus: SSRF enables internal network recon

CVE-2026-9557
6.4
EPSS 0.1%
Data ExtractionPrivacy ViolationPlugin
mautic/corePatch: 5.2.11CWE-918514
MEDIUM

OpenClaw: slash token revocation lag allows reuse

GHSA-4m3v-q747-pc6h
--
Auth BypassAgentPlugin
openclawPatch: 2026.4.24CWE-61333 ATLAS
MEDIUM

OpenClaw: Slack/Zalo webhook secrets outlive rotation

GHSA-275c-xpvc-jgfw
--
Auth BypassData LeakageAgentPlugin
openclawPatch: 2026.4.22CWE-61333 ATLAS
MEDIUM

OpenClaw: sandbox leaks host workspace path to child

GHSA-6c4r-g249-wv3c
--
Data LeakagePrivacy ViolationAgent
openclawPatch: 2026.4.26CWE-66832 ATLAS
MEDIUM

OpenClaw: QQBot slash commands bypass allowFrom auth

GHSA-77pv-3w4q-vrj5
--
Auth BypassAgentPlugin
openclawPatch: 2026.4.27CWE-86332 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