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 1431 results — has patch
MEDIUM

Strands Agents: world-readable session files in /tmp

GHSA-763v-5pjm-fx36
--
Data LeakageData ExtractionAgentFramework
strands-agentsPatch: 1.48.0CWE-2763.0K3 ATLAS
HIGH

LiteLLM: file read via vertex_ai_credentials alias

GHSA-g5ff-637f-6q2m
8.1
Data ExtractionData LeakageAuth BypassAPIInferenceFramework
litellmPatch: 1.95.0CWE-2065 ATLAS
MEDIUM

LiteLLM: reflected XSS in SSO debug callback

GHSA-hhww-mrg2-969h
6.8
Auth BypassData LeakageAPIFramework
litellmPatch: 1.85.0CWE-7963 ATLAS
MEDIUM

SiYuan: MCP file tool leaks publish-share passwords

CVE-2026-60083
4.9
EPSS 0.4%
Data LeakageAuth BypassPluginAgentAPI
github.com/siyuan-note/siyuan/kernelPatch: 0.0.0-20260808051406-3542530c505fCWE-8633.0K4 ATLAS
CRITICAL

MONAI: NaN/inf DICOM input causes DoS and corrupt inference

CVE-2026-48705
9.3
DoSAdversarial ExamplesFrameworkInferenceAPI
monaiPatch: 1.6.1CWE-201285 ATLAS
HIGHEXPLOIT AVAIL

Rembg: unauthenticated path traversal leaks files

CVE-2026-115924
8.6
EPSS 0.4%
Data ExtractionSupply ChainData LeakageFrameworkAPIInference
rembgPatch: 2.0.82CWE-221.1K5 ATLAS
MEDIUM

ONNX: unbounded alloc in 2/4-bit unpack causes DoS

CVE-2026-115922
6.2
EPSS 0.1%
DoSSupply ChainFrameworkModel
onnxPatch: 1.22.0CWE-7891.1K3 ATLAS
MEDIUM

ONNX: null deref/oversized alloc in Scan inference DoS

CVE-2026-115921
6.2
EPSS 0.1%
DoSSupply ChainFrameworkModel
onnxPatch: 1.22.0CWE-1951.1K3 ATLAS
MEDIUM

ONNX: ConvTranspose shape inference crash causes DoS

CVE-2026-115920
6.2
EPSS 0.2%
DoSSupply ChainFrameworkModel
onnxPatch: 1.22.0CWE-1251.1K3 ATLAS
MEDIUM

ONNX: OOB read in RNN shape inference crashes app

CVE-2026-115919
6.2
EPSS 0.2%
DoSSupply ChainFrameworkModel
onnxPatch: 1.22.0CWE-1251.1K2 ATLAS
MEDIUM

vLLM: chat template bypass enables DoS via /v1/responses

CVE-2026-115918
6.5
EPSS 0.4%
DoSInferenceAPI
vllmPatch: 0.32.0CWE-400943 ATLAS
LOW

vLLM: wildcard CORS lets web pages reach local servers

CVE-2026-115917
3.4
EPSS 0.2%
Data LeakageAuth BypassInferenceAPI
vllmPatch: 0.32.0CWE-942944 ATLAS
MEDIUM

vLLM: off-by-one token ID check crashes engine (DoS)

CVE-2026-115916
6.5
EPSS 0.3%
DoSInferenceFramework
vllmPatch: 0.32.0CWE-129942 ATLAS
MEDIUM

vLLM: Phi-4 audio attention causes GPU OOM DoS

CVE-2026-115913
6.5
EPSS 0.3%
DoSInferenceModel
vllmPatch: 0.32.0CWE-770943 ATLAS
HIGH

vLLM: pickle deserialization RCE via multimodal cache

CVE-2026-115912
7.5
EPSS 0.5%
Code ExecutionSupply ChainInferenceFramework
vllmPatch: 0.32.0CWE-502944 ATLAS
MEDIUM

vLLM: chat template DoS via unbounded Jinja rendering

CVE-2026-115911
6.5
EPSS 0.3%
DoSSupply ChainInferenceAPIFramework
vllmPatch: 0.32.0CWE-400944 ATLAS
HIGH

vLLM: image decoder abuse enables RCE/DoS

CVE-2026-115915
8.1
EPSS 0.7%
Code ExecutionDoSSupply ChainInferenceFrameworkAPI
vllmPatch: 0.32.0CWE-20945 ATLAS
MEDIUM

vLLM: zero-sum OCR image crashes engine (DoS)

CVE-2026-115914
6.5
EPSS 0.4%
DoSInferenceAPI
vllmPatch: 0.32.0CWE-617943 ATLAS
MEDIUM

filelock: rename-to-rmtree deletes other users' dirs

CVE-2026-112937
6.1
EPSS 0.2%
DoSSupply ChainFramework
filelockPatch: 4.2.1CWE-3676.3K1 ATLAS
LOW

filelock: Windows side-file planting breaks ReadWriteLock

CVE-2026-112913
3.3
DoSFramework
filelockPatch: 4.2.1CWE-3676.3K1 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