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 1346 results — Active exploitation, no patch
CRITICALEXPLOIT AVAIL

streamlit-geospatial: eval() injection enables RCE

CVE-2024-41115
9.8
EPSS 1.5%
Code ExecutionData ExtractionFramework
streamlit-geospatial3.1K5 ATLAS
CRITICALEXPLOIT AVAIL

streamlit-geospatial: RCE via eval() on palette input

CVE-2024-41114
9.8
EPSS 1.4%
Code ExecutionData ExtractionFrameworkInference
streamlit-geospatial3.1K4 ATLAS
CRITICALEXPLOIT AVAIL

streamlit-geospatial: RCE via eval() in Timelapse page

CVE-2024-41113
9.8
EPSS 1.4%
Code ExecutionData ExtractionFramework
streamlit-geospatial3.1K5 ATLAS
CRITICALEXPLOIT AVAIL

streamlit-geospatial: RCE via eval() on palette input

CVE-2024-41112
9.8
EPSS 1.4%
Code ExecutionFramework
streamlit-geospatial3.1K4 ATLAS
HIGHEXPLOIT AVAIL

TorchServe: default gRPC exposure allows unauth inference

CVE-2024-35199
8.2
EPSS 0.6%
DoSData ExtractionAuth BypassInferenceFramework
torchserve26.1K5 ATLAS
CRITICALEXPLOIT AVAIL

TorchServe: URL bypass enables arbitrary model loading

CVE-2024-35198
9.8
EPSS 0.8%
Auth BypassSupply ChainCode ExecutionInferenceFramework
torchserve26.1K5 ATLAS
HIGHEXPLOIT AVAIL

langchain-experimental: RCE via eval() in VectorSQL chain

CVE-2024-21513
8.5
EPSS 1.9%
Code ExecutionPrompt InjectionData ExtractionFrameworkRAGAgent
langchain-experimental3.2K5 ATLAS
LOWEXPLOIT AVAIL

ChatGPT macOS: cleartext conversation storage exposed

CVE-2024-40594
2.3
EPSS 0.1%
Data LeakagePrivacy ViolationAPI
3 ATLAS
UNKNOWNEXPLOIT AVAIL

lollms-webui: RCE via malicious GGUF model loading

CVE-2024-4897
--
EPSS 0.4%
Supply ChainCode ExecutionFrameworkModelInference
6 ATLAS
CRITICALEXPLOIT AVAIL

Gradio: code injection via component metadata (CVSS 9.8)

CVE-2024-39236
9.8
EPSS 0.9%
Code ExecutionSupply ChainFrameworkInference
gradio7354 ATLAS
MEDIUMEXPLOIT AVAIL

Flowise: reflected XSS enables credential theft

CVE-2024-37146
6.1
EPSS 0.4%
Data ExtractionAuth BypassSocial EngineeringAgentFramework
flowiseCWE-795 ATLAS
MEDIUMEXPLOIT AVAIL

Flowise: reflected XSS enables file read chain via chatflow

CVE-2024-37145
6.1
EPSS 0.5%
Code ExecutionData ExtractionPrivacy ViolationAgentFramework
flowiseCWE-795 ATLAS
MEDIUMEXPLOIT AVAIL

Flowise: reflected XSS in chatflow API enables session hijack

CVE-2024-36423
6.1
EPSS 0.4%
Data ExtractionAuth BypassCode ExecutionFrameworkAgent
flowiseCWE-795 ATLAS
MEDIUMEXPLOIT AVAIL

Flowise: reflected XSS enables session hijack and file read

CVE-2024-36422
6.1
EPSS 0.4%
Data LeakageData ExtractionFrameworkAgent
flowiseCWE-794 ATLAS
HIGHEXPLOIT AVAIL

Flowise: CORS wildcard enables file read and data theft

CVE-2024-36421
7.5
EPSS 8.5%
Data ExtractionAuth BypassData LeakageAgentFramework
flowiseCWE-3465 ATLAS
HIGHEXPLOIT AVAILSCANNER

Flowise: unauthenticated arbitrary file read via API

CVE-2024-36420
7.5
EPSS 1.8%
Data ExtractionAuth BypassData LeakageFrameworkAPIAgent
flowiseCWE-746 ATLAS
LOWEXPLOIT AVAIL

lollms-webui: CSRF allows unauthorized AI service install

CVE-2024-4839
3.3
EPSS 0.2%
Supply ChainAuth BypassInferenceFramework
lollms-webui4 ATLAS
MEDIUMEXPLOIT AVAILSCANNER

Gradio: open redirect enables phishing against ML users

CVE-2024-4940
6.1
EPSS 1.0%
Social EngineeringPrivacy ViolationFrameworkInference
gradio7355 ATLAS
HIGHEXPLOIT AVAIL

LangChain: Python REPL code execution without opt-in

CVE-2024-38459
7.8
EPSS 0.2%
Code ExecutionPrompt InjectionData ExtractionFrameworkAgent
langchain-experimental3.2K5 ATLAS
CRITICALEXPLOIT AVAILSCANNER

Langflow: unauthenticated RCE via custom component API

CVE-2024-37014
9.8
EPSS 63.7%
Code ExecutionAuth BypassSupply ChainFrameworkAgentAPI
langflowCWE-945 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