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
MEDIUMEXPLOIT AVAIL

llama-index: DocugamiReader MD5 hash collision drops chunks

CVE-2025-6211
6.5
EPSS 0.4%
Supply ChainData LeakageFrameworkRAG
llama-index-readers-docugamiPatch: 0.3.1CWE-4402514 ATLAS
HIGHEXPLOIT AVAIL

llama_index: path traversal allows arbitrary file read

CVE-2025-6209
7.5
EPSS 0.6%
Data ExtractionData LeakageFrameworkRAG
llama-index-corePatch: 0.12.41CWE-291.3K4 ATLAS
MEDIUMEXPLOIT AVAIL

llama-index Obsidian reader: hardlink path traversal leaks files

CVE-2025-6210
6.2
EPSS 0.3%
Data ExtractionSupply ChainFrameworkRAG
llama-index-readers-obsidianPatch: 0.5.2CWE-222513 ATLAS
MEDIUMEXPLOIT AVAIL

llama-index: JSONReader DoS via recursive JSON parsing

CVE-2025-5472
6.5
EPSS 0.4%
DoSFramework
llama-index-corePatch: 0.12.38CWE-6741.3K3 ATLAS
MEDIUMEXPLOIT AVAIL

llama-index ArxivReader: MD5 collision corrupts training data

CVE-2025-3044
5.3
EPSS 0.3%
Supply ChainModel PoisoningData LeakageFrameworkTraining DataRAG
llama-index-readers-papersPatch: 0.3.1CWE-4402515 ATLAS
HIGHEXPLOIT AVAIL

llama-index Papers Loader: XML expansion DoS

CVE-2025-3225
7.5
EPSS 0.5%
DoSSupply ChainFrameworkRAG
llama-index-readers-papersPatch: 0.3.2CWE-7762513 ATLAS
HIGHEXPLOIT AVAIL

LlamaIndex Obsidian: symlink traversal exposes host files

CVE-2025-3046
7.5
EPSS 0.6%
Data ExtractionData LeakageFrameworkRAG
llama-index-readers-obsidianPatch: 0.5.1CWE-222514 ATLAS
MEDIUMEXPLOIT AVAIL

llama-index: RCE via unsafe pickle deserialization

CVE-2025-3108
5.0
EPSS 0.5%
Code ExecutionSupply ChainFrameworkRAGAgent
llama-index-corePatch: 0.12.41CWE-11121.3K4 ATLAS
MEDIUM

MLflow: unauthenticated SSRF in gateway proxy

CVE-2025-52967
5.8
EPSS 0.4%
Auth BypassData ExtractionFrameworkAPI
mlflowPatch: 3.1.0CWE-9186954 ATLAS
CRITICALEXPLOIT AVAIL

llama_index: SQL injection in vector store integrations

CVE-2025-1793
9.8
EPSS 0.7%
Data ExtractionData LeakageSupply ChainFrameworkRAG
llama-indexPatch: 0.12.28CWE-892515 ATLAS
HIGHEXPLOIT AVAIL

jupyter_core: config hijack enables cross-user code exec

CVE-2025-30167
7.3
EPSS 0.2%
Code ExecutionSupply ChainData ExtractionFrameworkTraining Data
jupyter_corePatch: 5.8.1CWE-4271.9K4 ATLAS
MEDIUM

vllm: ReDoS in inference endpoints enables DoS

GHSA-j828-28rj-hfhp
4.3
DoSInferenceFramework
vllmPatch: 0.9.0CWE-1333943 ATLAS
HIGHEXPLOIT AVAIL

Label Studio: XSS enables unauthorized actions via CSRF

CVE-2025-47783
--
EPSS 0.6%
Code ExecutionData LeakageSocial EngineeringFrameworkTraining Data
label-studioPatch: 1.18.0CWE-7925 ATLAS
HIGHEXPLOIT AVAIL

llama_index: DoS via uncapped recursion in web reader

CVE-2025-1752
7.5
EPSS 0.5%
DoSFrameworkRAG
llama-indexPatch: 0.12.21CWE-4002513 ATLAS
CRITICALEXPLOIT AVAIL

browser-use: URL allowlist bypass enables SSRF in agents

CVE-2025-47241
9.3
EPSS 0.5%
Auth BypassData ExtractionAgentFramework
browser-usePatch: 0.1.45CWE-647755 ATLAS
HIGHEXPLOIT AVAIL

LLaMA-Factory: RCE via torch.load() unsafe deserialization

CVE-2025-46567
7.8
EPSS 0.3%
Code ExecutionSupply ChainFrameworkTraining Data
llamafactoryPatch: 0.9.3CWE-50235 ATLAS
CRITICAL

vLLM: RCE via malicious model, PyTorch < 2.6 bypass

GHSA-ggpf-24jw-3fcw
9.8
Code ExecutionSupply ChainFrameworkInferenceModel
vllmPatch: 0.8.0CWE-1395945 ATLAS
MEDIUM

vLLM: DoS via unbounded XGrammar schema cache

GHSA-hf3c-wxg2-49q9
6.5
DoSSupply ChainInferenceFrameworkAPI
vllmPatch: 0.8.4CWE-770945 ATLAS
CRITICALEXPLOIT AVAIL

jupyter-remote-desktop-proxy: VNC network exposure

CVE-2025-32428
--
EPSS 0.9%
Auth BypassData LeakagePrivacy ViolationFramework
jupyter-remote-desktop-proxyPatch: 3.0.1CWE-6681.9K5 ATLAS
MEDIUM

xgrammar: unbounded grammar cache causes LLM server DoS

CVE-2025-32381
6.5
EPSS 0.5%
DoSInferenceFramework
xgrammarPatch: 0.1.18CWE-7701323 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