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 1908 results — High severity
HIGHEXPLOIT AVAIL

picklescan: detection bypass enables RCE via pickle files

CVE-2025-71378
8.1
EPSS 0.5%
Supply ChainCode ExecutionModelFramework
picklescanCWE-50234 ATLAS
HIGHEXPLOIT AVAIL

picklescan: detection bypass enables RCE via malicious models

CVE-2025-71357
8.1
EPSS 0.4%
Supply ChainCode ExecutionModelFramework
picklescanCWE-50235 ATLAS
HIGHEXPLOIT AVAIL

picklescan: scanner bypass enables RCE via pickle files

CVE-2025-71351
--
EPSS 0.6%
Supply ChainCode ExecutionModelFramework
picklescanCWE-18434 ATLAS
HIGHEXPLOIT AVAIL

picklescan: scanner bypass enables supply chain RCE

CVE-2025-71348
8.1
EPSS 0.6%
Supply ChainCode ExecutionModelFramework
picklescanCWE-50235 ATLAS
HIGHEXPLOIT AVAIL

litellm: auth bypass in SSO debug exposes LLM proxy

CVE-2026-12795
7.3
EPSS 0.8%
Auth BypassData ExtractionCode ExecutionInferenceAPIFramework
litellmCWE-28765 ATLAS
HIGHEXPLOIT AVAIL

litellm: auth bypass in MCP proxy, no credentials required

CVE-2026-12773
7.3
EPSS 1.0%
Auth BypassData ExtractionData LeakageAPIInferenceAgent
litellmPatch: 1.84.0CWE-28765 ATLAS
HIGHEXPLOIT AVAIL

litellm: JWT auth bypass in M2M proxy handler

CVE-2026-12771
7.5
EPSS 0.4%
Auth BypassInferenceAPI
litellmCWE-26665 ATLAS
HIGHEXPLOIT AVAIL

litellm: auth bypass in Admin Key Handler endpoint

CVE-2026-12770
8.8
EPSS 0.6%
Auth BypassDoSInferenceAPI
litellmCWE-26664 ATLAS
HIGHEXPLOIT AVAIL

vLLM: sparse tensor DoS/memory corruption via embeddings

CVE-2026-56340
7.5
EPSS 0.6%
DoSCode ExecutionInferenceAPI
vllmCWE-20945 ATLAS
HIGH

vLLM: ReDoS via crafted API input causes DoS

CVE-2025-71379
7.5
EPSS 0.5%
DoSInferenceAPI
vllmCWE-1333944 ATLAS
HIGH

Gogs: XSS via outdated Jupyter renderer, account takeover

GHSA-6vxv-wg6j-5qwp
--
Supply ChainCode ExecutionAuth BypassFramework
gogs.io/gogsPatch: 0.14.3CWE-803.0K4 ATLAS
HIGH

mcp-searxng: SSRF via DNS rebinding in web_url_read

GHSA-mrvx-jmjw-vggc
7.1
Data ExtractionAuth BypassAgentPlugin
CWE-9185 ATLAS
HIGH

mcp-searxng: DoS via unbounded URL response read

GHSA-xcqx-9jf5-w339
7.5
DoSPrompt InjectionAgentPlugin
CWE-4004 ATLAS
HIGHEXPLOIT AVAIL

Langflow: pre-auth DoS via malformed multipart boundary

CVE-2026-55446
7.5
EPSS 0.6%
DoSAuth BypassFramework
langflowPatch: 1.0.19CWE-4003 ATLAS
HIGHEXPLOIT AVAIL

jupyterlab-git: excluded_paths bypass exposes secrets

CVE-2026-54528
7.1
EPSS 0.4%
Auth BypassData ExtractionFrameworkPlugin
jupyterlab-gitPatch: 0.54.0CWE-1781.9K5 ATLAS
HIGHEXPLOIT AVAIL

Stanza: pickle fallback bypass enables model RCE

CVE-2026-54499
7.5
EPSS 0.5%
Supply ChainCode ExecutionModelFramework
torchCWE-50226.1K5 ATLAS
HIGHEXPLOIT AVAIL

Home Assistant Konnected: auth bypass leaks alarm panel state

CVE-2026-54317
7.6
EPSS 0.3%
Auth BypassData ExtractionDoSPlugin
homeassistantPatch: 2026.6.0CWE-2005144 ATLAS
HIGH

containerd: symlink follow leaks host files via kubectl logs

CVE-2026-53489
--
EPSS 0.2%
Data ExtractionSupply ChainInferenceFramework
github.com/containerd/containerd/v2Patch: 2.1.9CWE-616.3K5 ATLAS
HIGH

containerd: label injection enables host RCE via CRI plugin

CVE-2026-53488
--
EPSS 0.2%
Supply ChainCode ExecutionInferencePlugin
github.com/containerd/containerd/v2Patch: 2.0.10CWE-746.3K5 ATLAS
HIGHEXPLOIT AVAIL

libaom: AV1 SVC OOB write enables RCE

CVE-2026-56211
7.1
EPSS 0.9%
Code ExecutionSupply ChainInference
rhaiis/vllm-cpu-rhel9942 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