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 533 results — Critical severity
CRITICAL

guardrails-ai: RCE via malicious Hub package manifest

CVE-2026-31233
9.8
EPSS 0.6%
Supply ChainCode ExecutionFrameworkPlugin
guardrails-aiCWE-94785 ATLAS
CRITICAL

mamba: RCE via unsafe torch.load() on model load

CVE-2026-31239
9.8
EPSS 0.4%
Supply ChainCode ExecutionFrameworkModel
mamba-ssmCWE-50226.1K5 ATLAS
CRITICAL

Ludwig: RCE via unsafe pickle deserialization in model serve

CVE-2026-31238
9.8
EPSS 0.5%
Code ExecutionSupply ChainFrameworkModelInference
ludwigCWE-50226.1K4 ATLAS
CRITICAL

ART: torch.load() RCE via insecure deserialization

CVE-2026-31229
9.8
EPSS 0.6%
Supply ChainCode ExecutionFrameworkModel
4 ATLAS
CRITICALEXPLOIT AVAIL

openclaude: sandbox bypass allows host-level RCE

CVE-2026-42074
--
EPSS 0.6%
Prompt InjectionCode ExecutionAuth BypassAgentFrameworkPlugin
openclaudePatch: 0.5.1CWE-2846.3K6 ATLAS
CRITICAL

torch-checkpoint: unsafe pickle deserialization RCE

CVE-2026-31214
9.8
EPSS 0.5%
Code ExecutionSupply ChainModelTraining Data
4 ATLAS
CRITICALEXPLOIT AVAIL

Flowise: SSRF in agent tools bypasses security wrapper

CVE-2026-43995
9.8
EPSS 0.4%
Code ExecutionData ExtractionAuth BypassAgentFrameworkPlugin
flowise5 ATLAS
CRITICALEXPLOIT AVAIL

PraisonAI: MCP path traversal escalates to full RCE

CVE-2026-44336
9.6
EPSS 0.6%
Prompt InjectionCode ExecutionData ExtractionAgentPluginFramework
PraisonAIPatch: 4.6.34CWE-2018 ATLAS
CRITICALEXPLOIT AVAIL

cline: WebSocket auth bypass enables terminal RCE

CVE-2026-44211
9.6
EPSS 0.2%
Auth BypassCode ExecutionData LeakageAgentPlugin
clineCWE-30627 ATLAS
CRITICALSCANNER

open-webui: LDAP auth bypass — full account takeover

CVE-2026-44551
9.1
EPSS 1.5%
Auth BypassData ExtractionFrameworkAPI
open-webuiPatch: 0.9.0CWE-28724 ATLAS
CRITICALKEVSCANNER

LiteLLM: SQL injection exposes LLM API credentials

CVE-2026-42208
9.8
EPSS 89.4%
Auth BypassData ExtractionSupply ChainAPIInference
litellmCWE-8965 ATLAS
CRITICALEXPLOIT AVAIL

vm2: sandbox escape via nesting:true enables RCE

CVE-2026-44007
9.1
EPSS 1.0%
Code ExecutionAuth BypassAgentFramework
vm2Patch: 3.11.1CWE-2841.9K5 ATLAS
CRITICAL

OpenClaw: TOCTOU symlink race escapes OpenShell sandbox

CVE-2026-44112
9.6
EPSS 7.3%
Code ExecutionSupply ChainAgentFrameworkPlugin
OpenClaw34 ATLAS1 incident
CRITICALEXPLOIT AVAIL

Langflow: path traversal allows arbitrary directory deletion

CVE-2026-42048
9.6
EPSS 4.2%
DoSAuth BypassFrameworkRAG
langflowPatch: 1.9.0CWE-223 ATLAS
CRITICAL

Ollama: heap OOB read leaks API keys and chat data

CVE-2026-7482
9.1
EPSS 2.2%
Data ExtractionData LeakageAuth BypassInferenceModel
ollama1.9K5 ATLAS
CRITICALEXPLOIT AVAIL

Ollama: path traversal + unsigned update = silent RCE

CVE-2026-42249
9.8
EPSS 1.0%
Code ExecutionSupply ChainInference
ollamaCWE-221.9K4 ATLAS
CRITICALEXPLOIT AVAIL

Ollama: silent auto-update bypasses signature check on Windows

CVE-2026-42248
9.8
EPSS 0.7%
Supply ChainCode ExecutionInference
ollamaCWE-4941.9K5 ATLAS
CRITICAL

Gemini CLI: RCE via malicious workspace in CI/CD

GHSA-wpqr-6v78-jr5g
10.0
Code ExecutionPrompt InjectionSupply ChainAgentFramework
@google/gemini-cliPatch: 0.39.1CWE-207 ATLAS
CRITICAL

litellm: SQLi exposes all managed LLM API credentials

GHSA-r75f-5x8p-qvmc
--
Auth BypassData ExtractionInferenceAPI
litellmPatch: 1.83.7CWE-8965 ATLAS
CRITICALEXPLOIT AVAIL

Flowise: Cypher injection via GraphCypherQAChain node

CVE-2026-41274
9.8
EPSS 0.5%
Data ExtractionCode ExecutionAgentFramework
flowiseCWE-9435 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