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 325 results — Critical severity, Active exploitation
CRITICALEXPLOIT AVAIL

LMDeploy: unauthenticated RCE via pickle in /update_weights

CVE-2026-119706
9.8
EPSS 1.0%
Code ExecutionAuth BypassInferenceAPIFramework
lmdeployCWE-50214 ATLAS
CRITICALEXPLOIT AVAIL

Langflow: improper authentication allows remote bypass

CVE-2026-93680
9.8
EPSS 2.2%
Auth BypassData LeakageCode ExecutionFrameworkAgentRAG
langflowCWE-2873 ATLAS
CRITICALEXPLOIT AVAIL

PraisonAI: unauthenticated AgentOS chat API drives agents

CVE-2026-57116
9.8
EPSS 0.4%
Auth BypassData LeakageData ExtractionAgentAPIFramework
praisonaiCWE-20016 ATLAS
CRITICALEXPLOIT AVAIL

Pillow: heap overflow via lossless JPEG in thumbnail()

CVE-2026-112403
--
EPSS 0.9%
DoSCode ExecutionSupply ChainFrameworkInferenceTraining Data
PillowPatch: 13.0.0CWE-1226.3K3 ATLAS
CRITICALEXPLOIT AVAILSCANNER

Langchain-Chatchat: unauthenticated shell tool RCE

CVE-2026-75128
9.8
EPSS 2.2%
Code ExecutionAuth BypassFrameworkAgentPlugin
CWE-3064 ATLAS
CRITICALEXPLOIT AVAIL

Mercury: regex blocklist bypass allows unauthenticated RCE

CVE-2026-111057
10.0
EPSS 0.7%
Auth BypassCode ExecutionFrameworkPlugin
mercuryPatch: 3.2.4CWE-1853.0K4 ATLAS
CRITICALEXPLOIT AVAIL

DataBuff APM: hard-coded admin credentials allow full takeover

CVE-2026-111693
9.8
EPSS 0.5%
Auth BypassData LeakageFrameworkAPI
4 ATLAS
CRITICALEXPLOIT AVAIL

DataBuff ai-apm-web: hardcoded JWT secret enables admin bypass

CVE-2026-111692
9.8
EPSS 0.6%
Auth BypassData ExtractionFrameworkAPI
3 ATLAS
CRITICALEXPLOIT AVAIL

PraisonAI agents: unauthenticated access to agent endpoints

CVE-2026-57118
9.8
EPSS 0.4%
Auth BypassData LeakageCode ExecutionAgentFrameworkAPI
praisonaiagentsCWE-306206 ATLAS
CRITICALEXPLOIT AVAIL

PraisonAI: code injection in deploy API enables RCE

CVE-2026-62176
9.1
EPSS 0.5%
Code ExecutionSupply ChainFrameworkAgentAPI
PraisonAIPatch: 4.6.78CWE-9414 ATLAS
CRITICALEXPLOIT AVAILSCANNER

Langflow: OS command injection allows remote RCE

CVE-2026-93674
9.8
EPSS 15.3%
Code ExecutionData LeakageFrameworkAgent
langflowCWE-944 ATLAS
CRITICALEXPLOIT AVAILSCANNER

Langflow: MCP Stdio command injection gives authenticated RCE

CVE-2026-105740
9.9
EPSS 3.9%
Code ExecutionSupply ChainFrameworkAgentPlugin
langflowCWE-784 ATLAS
CRITICALEXPLOIT AVAIL

Langflow: MCP stdio command injection allows host RCE

CVE-2026-105697
9.9
EPSS 0.9%
Code ExecutionAuth BypassFrameworkAgentPlugin
lfxPatch: 1.10.3CWE-786 ATLAS1 incident
CRITICALEXPLOIT AVAIL

Langchain-Chatchat: path traversal enables arbitrary file write

CVE-2026-51884
9.8
EPSS 0.6%
Code ExecutionData LeakageFrameworkRAGAPI
3 ATLAS
CRITICALEXPLOIT AVAIL

Langchain-Chatchat: path traversal allows arbitrary file write

CVE-2026-51883
9.1
EPSS 0.4%
Code ExecutionSupply ChainFrameworkRAG
2 ATLAS
CRITICALEXPLOIT AVAIL

Langchain-Chatchat: path traversal in /v1/files file write

CVE-2026-51882
9.1
EPSS 0.5%
Code ExecutionAuth BypassAPIFrameworkRAG
3 ATLAS
CRITICALEXPLOIT AVAIL

vm2: node:sqlite sandbox escape allows native code RCE

CVE-2026-92938
9.9
EPSS 0.6%
Code ExecutionSupply ChainPluginAgentFramework
vm2Patch: 3.11.7CWE-6933.0K3 ATLAS
CRITICALEXPLOIT AVAIL

vm2: native code exec via crypto.setEngine sandbox escape

CVE-2026-92939
9.9
EPSS 0.6%
Code ExecutionSupply ChainPluginAgentFramework
vm2Patch: 3.11.7CWE-1143.0K3 ATLAS
CRITICALEXPLOIT AVAIL

aaPanel BaoTa: command injection in file merge handler

CVE-2026-101008
9.1
EPSS 2.3%
Code ExecutionFramework
2 ATLAS
CRITICALEXPLOIT AVAIL

Decepticon: ChatML token injection yields sandbox RCE

CVE-2026-61732
10.0
EPSS 1.5%
Prompt InjectionCode ExecutionAgentFrameworkInference
decepticon-sdkPatch: 1.1.17CWE-74946 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