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
4,330

AI/ML CVEs Tracked

535

Critical

107

New This Week

25

In CISA KEV

Sort:DateCVSSEPSSKEV firstMost exploited
Filter:AllCriticalHighMediumKEV onlyActive exploitationHas patchNo patch

Latest AI Security Threats

Showing 20 of 4330 results
HIGHEXPLOIT AVAIL

Kubeflow: token theft lets any user hijack accounts

CVE-2026-47237
8.0
EPSS 0.4%
Auth BypassData LeakageFrameworkAPI
CWE-2663 ATLAS
MEDIUMEXPLOIT AVAIL

Gitea: LFS deploy-key flaw leaks private repo objects

CVE-2026-58435
5.4
EPSS 0.3%
Auth BypassData LeakageTraining DataModel
code.gitea.io/giteaPatch: 1.27.0CWE-2666.3K3 ATLAS
HIGH

MCP Toolbox: SQLi bypasses BigQuery allowedDatasets ACL

CVE-2026-15829
--
EPSS 0.2%
Auth BypassData LeakageCode ExecutionAgentPluginAPI
3 ATLAS
CRITICALEXPLOIT AVAIL

Grav CMS API plugin: forged keys enable account takeover

CVE-2026-65007
9.6
EPSS 0.3%
Auth BypassPluginAPI
CWE-862
MEDIUMEXPLOIT AVAIL

WPBot: missing auth check lets subscribers edit RAG config

CVE-2026-14185
4.3
EPSS 0.3%
Auth BypassData LeakagePluginRAG
2 ATLAS
UNKNOWNEXPLOIT AVAIL

AgenticMail: unauthenticated email hijacks AI agent

CVE-2026-57495
--
EPSS 0.4%
Prompt InjectionAuth BypassCode ExecutionAgentPlugin
CWE-3065 ATLAS
HIGHEXPLOIT AVAIL

Pillow: OOB read/DoS via unchecked mmap stride (McIdas)

CVE-2026-54058
--
EPSS 0.5%
Data LeakageDoSInferenceTraining DataPlugin
pillowPatch: 12.3.0CWE-1252 ATLAS
MEDIUM

@ai-sdk/harness-codex: tool relay authz bypass

CVE-2026-64650
--
EPSS 0.2%
Auth BypassCode ExecutionSupply ChainAgentPlugin
3 ATLAS
CRITICALEXPLOIT AVAIL

GPT-SoVITS: unauthenticated RCE via webui.py

CVE-2026-63766
9.8
EPSS 2.1%
Code ExecutionInferenceFramework
CWE-782 ATLAS
CRITICALEXPLOIT AVAIL

ktransformers: unauth pickle RCE via ZMQ socket

CVE-2026-63767
9.8
EPSS 1.1%
Code ExecutionAuth BypassInferenceFramework
ktransformers9.8K3 ATLAS
MEDIUM

onenote_parser: path traversal via crafted .onetoc2 file

CVE-2026-46671
4.4
EPSS 0.2%
DoSData LeakagePlugin
CWE-222 ATLAS
MEDIUMEXPLOIT AVAIL

GLib GDBus: unbounded auth line enables local DoS

CVE-2026-15588
5.3
EPSS 0.5%
DoSInferenceFramework
rhaiis/vllm-cuda-rhel9942 ATLAS
HIGHEXPLOIT AVAIL

Keras: unsafe pickle deserialization allows RCE

CVE-2026-12484
7.8
EPSS 0.3%
Code ExecutionSupply ChainFrameworkModel
kerasPatch: 3.12.3CWE-5024.1K3 ATLAS
UNKNOWNEXPLOIT AVAIL

Lollms: stored XSS in prompt-share DM inbox

CVE-2026-12228
--
EPSS 0.3%
Code ExecutionData LeakageFramework
parisneo/lollms2 ATLAS
HIGH

dd-trace: unbounded W3C baggage parsing enables DoS

CVE-2026-50272
7.5
EPSS 0.8%
DoSAPI
CWE-7702 ATLAS
HIGH

dd-trace-py: unbounded baggage header parsing causes DoS

CVE-2026-50271
7.5
EPSS 0.8%
DoSFrameworkAPI
CWE-7703 ATLAS
CRITICAL

Langflow: hard-coded credentials enable takeover

CVE-2026-13446
9.8
EPSS 0.4%
Auth BypassCode ExecutionFrameworkAgent
langflowCWE-7983 ATLAS
HIGH

Langflow: SaveToFile flaw breaks user storage isolation

CVE-2026-13445
8.1
EPSS 0.4%
Auth BypassData LeakagePrivacy ViolationFrameworkPlugin
langflowCWE-6393 ATLAS
CRITICAL

Langflow: path traversal writes arbitrary files

CVE-2026-8859
9.9
EPSS 0.6%
Code ExecutionFrameworkAgentPlugin
langflowCWE-222 ATLAS
CRITICAL

Langflow: DB manipulation escalates to superuser RCE

CVE-2026-8635
9.9
EPSS 0.6%
Auth BypassCode ExecutionFrameworkAgent
langflowCWE-944 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