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 615 results — Active exploitation, has patch
HIGHEXPLOIT AVAIL

langgraph-checkpoint: Deserialization enables RCE

CVE-2025-64439
--
EPSS 0.9%
Code ExecutionSupply ChainFrameworkAgent
langgraph-checkpointPatch: 3.0.0CWE-5024.1K5 ATLAS
CRITICALEXPLOIT AVAIL

keras: Path Traversal enables file access

CVE-2025-12060
9.8
EPSS 0.6%
Supply ChainCode ExecutionFrameworkTraining Data
kerasPatch: 3.12.0CWE-224.1K4 ATLAS
HIGHEXPLOIT AVAIL

langgraph-checkpoint-sqlite: SQL Injection exposes database

CVE-2025-64104
7.3
EPSS 0.2%
Auth BypassData ExtractionData LeakageFrameworkAgent
langgraph-checkpoint-sqlitePatch: 2.0.11CWE-894.1K4 ATLAS
MEDIUMEXPLOIT AVAIL

Keras: safe_mode bypass enables file read and SSRF

CVE-2025-12058
--
EPSS 0.2%
Data ExtractionSupply ChainCode ExecutionFrameworkModel
kerasPatch: 3.12.0CWE-5024.1K5 ATLAS
HIGHEXPLOIT AVAIL

langgraph-checkpoint-sqlite: SQL Injection exposes database

CVE-2025-8709
7.3
EPSS 0.2%
Data ExtractionAuth BypassData LeakageFrameworkAgent
langgraph-checkpoint-sqlitePatch: 2.0.11CWE-894.1K5 ATLAS
CRITICALEXPLOIT AVAIL

keras: Deserialization enables RCE

CVE-2025-49655
9.8
EPSS 0.8%
Code ExecutionSupply ChainFrameworkModel
kerasPatch: 3.11.3CWE-5024.1K5 ATLAS
HIGHEXPLOIT AVAIL

vLLM: SSRF in media loader exposes internal network

CVE-2025-6242
7.1
EPSS 0.3%
Data ExtractionAuth BypassInferenceFramework
vllmPatch: 0.11.0CWE-601944 ATLAS
HIGHEXPLOIT AVAIL

LLaMA-Factory: SSRF+LFI in multimodal chat API

CVE-2025-61784
8.1
EPSS 0.4%
Data ExtractionPrivacy ViolationCode ExecutionFrameworkAPITraining Data
llamafactoryPatch: 0.9.4CWE-91836 ATLAS
HIGHEXPLOIT AVAIL

langchain-text-splitters: XXE enables arbitrary file read

CVE-2025-6985
7.5
EPSS 0.5%
Data ExtractionSupply ChainData LeakageFrameworkRAGAgent
langchain-text-splittersPatch: 0.3.9CWE-6113.2K5 ATLAS
MEDIUMEXPLOIT AVAIL

clearml: path traversal in safe_extract → RCE risk

CVE-2025-8917
5.8
EPSS 0.5%
Supply ChainCode ExecutionFrameworkTraining Data
clearmlPatch: 2.0.2CWE-22234 ATLAS
HIGHEXPLOIT AVAIL

llama-index-core: insecure /tmp dir, model theft risk

CVE-2025-7647
7.3
EPSS 0.1%
Data ExtractionModel PoisoningSupply ChainFrameworkRAG
llama-index-corePatch: 0.13.0CWE-3781.3K5 ATLAS
HIGHEXPLOIT AVAIL

Picklescan: CRC bypass hides malicious pickle in ZIP

CVE-2025-10156
7.5
EPSS 1.5%
Supply ChainCode ExecutionModelFramework
picklescanPatch: 0.0.31CWE-69335 ATLAS1 incident
HIGHEXPLOIT AVAIL

PickleScan: subclass bypass enables malicious model RCE

CVE-2025-10157
8.3
EPSS 0.8%
Supply ChainCode ExecutionModelFramework
picklescanPatch: 0.0.31CWE-69335 ATLAS1 incident
HIGHEXPLOIT AVAIL

MONAI: unsafe pickle deserialization RCE in data pipeline

CVE-2025-58757
8.8
EPSS 0.6%
Code ExecutionSupply ChainFrameworkTraining Data
monaiPatch: 1.5.1CWE-5021285 ATLAS
HIGHEXPLOIT AVAIL

MONAI: unsafe deserialization in CheckpointLoader allows RCE

CVE-2025-58756
8.8
EPSS 0.8%
Code ExecutionSupply ChainFrameworkTraining Data
monaiPatch: 1.5.1CWE-5021285 ATLAS
HIGHEXPLOIT AVAIL

MONAI: path traversal allows arbitrary file write

CVE-2025-58755
8.8
EPSS 0.6%
Supply ChainCode ExecutionFramework
monaiPatch: 1.5.1CWE-221284 ATLAS
MEDIUMEXPLOIT AVAIL

xgrammar: DoS via oversized JSON schema grammar parsing

CVE-2025-58446
--
EPSS 0.6%
DoSInferenceFramework
xgrammarPatch: 0.1.24CWE-7701323 ATLAS
HIGHEXPLOIT AVAILSCANNER

EverNoteLoader: XXE exposes host files in LangChain

CVE-2025-6984
7.5
EPSS 1.6%
Data ExtractionData LeakageFrameworkRAG
langchain-communityPatch: 0.3.27CWE-2001.3K4 ATLAS
HIGHEXPLOIT AVAIL

llama-index: JSON parsing DoS via deep recursion

CVE-2025-5302
8.6
EPSS 0.3%
DoSFrameworkRAG
llama-index-corePatch: 0.12.38CWE-6741.3K3 ATLAS
HIGHEXPLOIT AVAIL

xgrammar: uncontrolled recursion in grammar parsing causes DoS

CVE-2025-57809
7.5
EPSS 0.5%
DoSSupply ChainFrameworkInference
xgrammarPatch: 0.1.21CWE-6741323 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