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

BentoML: malicious bento archive RCE via Jinja2 SSTI

CVE-2026-35044
8.8
EPSS 0.4%
Supply ChainCode ExecutionFramework
bentomlPatch: 1.4.38CWE-1336235 ATLAS
HIGHEXPLOIT AVAIL

BentoML: cmd injection RCE on cloud build infra

CVE-2026-35043
7.8
EPSS 0.3%
Supply ChainCode ExecutionFramework
bentomlPatch: 1.4.38CWE-78235 ATLAS
HIGHEXPLOIT AVAILSCANNER

LiteLLM: auth bypass allows RCE and full takeover

CVE-2026-35029
8.8
EPSS 38.6%
Auth BypassCode ExecutionData ExtractionFrameworkAPIInference
litellmPatch: 1.83.0CWE-86366 ATLAS
HIGH

oauthenticator: auth bypass enables JupyterHub account takeover

CVE-2026-33175
8.8
EPSS 0.4%
Auth BypassFramework
CWE-2874 ATLAS
HIGH

Ajenti: missing authz lets any user install packages

CVE-2026-35175
--
EPSS 0.3%
Auth BypassSupply ChainCode ExecutionFrameworkPlugin
CWE-8624 ATLAS
HIGH

vLLM: audio downmix mismatch enables adversarial input

CVE-2026-34760
7.1
EPSS 0.3%
Adversarial ExamplesSupply ChainInferenceFramework
vllmPatch: 0.18.0CWE-20944 ATLAS
HIGH

onnx: TOCTOU symlink following enables arbitrary file write

GHSA-q56x-g2fj-4rj6
7.1
Supply ChainCode ExecutionFrameworkModel
onnxPatch: 1.21.0CWE-221.1K4 ATLAS
HIGHEXPLOIT AVAIL

praisonaiagents: SSRF leaks cloud IAM credentials

CVE-2026-34954
8.6
EPSS 0.4%
Prompt InjectionData ExtractionAgentFramework
praisonaiagentsPatch: 1.5.95CWE-918205 ATLAS
HIGHEXPLOIT AVAIL

PraisonAI: sandbox escape via shell=True blocklist bypass

CVE-2026-34955
8.8
EPSS 0.4%
Code ExecutionPrompt InjectionAuth BypassAgentFrameworkPlugin
praisonaiPatch: 4.5.97CWE-7816 ATLAS1 incident
HIGHEXPLOIT AVAIL

PraisonAI: SSRF via api_base steals cloud IAM credentials

CVE-2026-34936
7.7
EPSS 0.4%
Data ExtractionAuth BypassSupply ChainFrameworkAPIAgent
praisonaiPatch: 4.5.90CWE-91815 ATLAS
HIGHEXPLOIT AVAIL

PraisonAI: OS command injection via run_python() shell escape

CVE-2026-34937
7.8
EPSS 0.6%
Code ExecutionPrompt InjectionAuth BypassAgentFrameworkPlugin
praisonaiagentsPatch: 1.5.90CWE-78206 ATLAS1 incident
HIGHEXPLOIT AVAIL

Open WebUI: access control bypass leaks Tool Valve API keys

CVE-2026-34222
7.7
EPSS 5.1%
Auth BypassData ExtractionAgentPluginFramework
open-webuiPatch: 0.8.11CWE-28525 ATLAS
HIGH

ONNX: property overwrite via crafted model file

CVE-2026-34445
8.6
EPSS 0.3%
Supply ChainDoSCode ExecutionFrameworkModelInference
onnxPatch: 1.21.0CWE-201.1K5 ATLAS
HIGHEXPLOIT AVAIL

ONNX: symlink path traversal allows arbitrary file read

CVE-2026-27489
8.6
EPSS 0.6%
Supply ChainData ExtractionFrameworkModel
onnxPatch: 1.21.0CWE-231.1K5 ATLAS
HIGH

Claude Setup: DLL search-order hijacking LPE

CVE-2026-22561
7.8
EPSS 0.2%
Code ExecutionSupply ChainAPIFramework
3 ATLAS
HIGH

OpenClaw: SSRF in fal provider exposes internal services

CVE-2026-34504
8.3
EPSS 0.2%
Supply ChainData ExtractionPrivacy ViolationAgentPluginAPI
OpenClaw34 ATLAS1 incident
HIGH

OpenClaw: WebSocket session persists after token revocation

CVE-2026-34503
8.1
EPSS 0.3%
Auth BypassData ExtractionAgent
OpenClaw33 ATLAS1 incident
HIGH

OpenClaw: scope bypass lets low-priv ops elevate node access

CVE-2026-33577
8.1
EPSS 0.4%
Auth BypassData ExtractionAgentFramework
OpenClaw34 ATLAS1 incident
HIGH

OpenClaw: sandbox escape via fs-bridge TOCTOU race

CVE-2026-32988
7.5
EPSS 0.1%
Auth BypassCode ExecutionAgentFramework
OpenClaw34 ATLAS1 incident
HIGH

OpenClaw: Telegram bot token leaked in media fetch errors

CVE-2026-32982
7.5
EPSS 0.4%
Data LeakageAuth BypassAgent
OpenClaw34 ATLAS1 incident

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