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 4307 results
CRITICALEXPLOIT AVAIL

Affiliator WP Plugin: Unauthenticated Web Shell Upload

CVE-2024-49326
9.8
EPSS 0.5%
Code ExecutionAuth BypassSupply ChainFrameworkAPI
affiliator4.1K6 ATLAS
MEDIUMEXPLOIT AVAIL

lollms: path traversal allows arbitrary directory read

CVE-2024-6985
4.4
EPSS 0.4%
Data ExtractionAuth BypassFrameworkAgent
lollmsCWE-234 ATLAS
LOWEXPLOIT AVAIL

lollms: path traversal in RAG database functions

CVE-2024-6971
3.4
EPSS 0.3%
Data ExtractionCode ExecutionRAGFrameworkAgent
lollmsCWE-224 ATLAS
MEDIUM

Gradio: stored XSS via malicious file upload

CVE-2024-47872
5.4
EPSS 0.3%
Data ExtractionPrivacy ViolationFrameworkInference
gradioCWE-797355 ATLAS
CRITICAL

Gradio: cleartext MITM exposes ML demo data via share=True

CVE-2024-47871
9.1
EPSS 0.2%
Data ExtractionData LeakagePrivacy ViolationFrameworkInferenceAPI
gradioCWE-3117354 ATLAS
HIGH

Gradio: race condition enables backend URL hijacking

CVE-2024-47870
8.1
EPSS 0.4%
Data ExtractionPrivacy ViolationAuth BypassFrameworkInference
gradioCWE-3627354 ATLAS
LOW

Gradio: timing attack exposes analytics dashboard auth

CVE-2024-47869
3.7
EPSS 0.3%
Auth BypassData ExtractionFrameworkAPI
gradioCWE-2037353 ATLAS
HIGHEXPLOIT AVAIL

Gradio: path traversal leaks arbitrary server files

CVE-2024-47868
7.5
EPSS 0.8%
Data ExtractionData LeakageFrameworkInference
gradioCWE-227355 ATLAS
HIGH

Gradio: no integrity check on FRP binary, supply chain RCE

CVE-2024-47867
7.5
EPSS 0.2%
Supply ChainCode ExecutionFramework
gradioCWE-3457353 ATLAS
MEDIUM

Gradio: monitoring endpoint bypass leaks app analytics

CVE-2024-47168
4.3
EPSS 0.3%
Data LeakagePrivacy ViolationAuth BypassFrameworkInference
gradioCWE-6707353 ATLAS
CRITICAL

Gradio: unauthenticated SSRF in /queue/join, internal pivot

CVE-2024-47167
9.8
EPSS 0.5%
Data ExtractionAuth BypassCode ExecutionFrameworkInference
gradioCWE-9187354 ATLAS
MEDIUM

Gradio: path traversal leaks custom component source

CVE-2024-47166
5.3
EPSS 0.4%
Data ExtractionData LeakageFramework
gradioCWE-227354 ATLAS
MEDIUM

Gradio: CORS null origin bypass leaks auth tokens

CVE-2024-47165
5.4
EPSS 0.3%
Auth BypassData ExtractionFrameworkAPI
gradioCWE-2857353 ATLAS
MEDIUM

Gradio: path traversal bypasses directory access controls

CVE-2024-47164
6.5
EPSS 0.7%
Data ExtractionAuth BypassFrameworkInference
gradioCWE-227355 ATLAS
HIGH

Gradio: CORS bypass exposes local instances to credential theft

CVE-2024-47084
8.3
EPSS 0.5%
Auth BypassData ExtractionData LeakageFrameworkInference
gradioCWE-2857355 ATLAS
MEDIUM

Gradio: Dropdown validation bypass enables arbitrary input

GHSA-26jh-r8g2-6fpr
5.3
Auth BypassCode ExecutionFrameworkInferenceAPI
gradioPatch: 5.0.07353 ATLAS
MEDIUMEXPLOIT AVAIL

open-webui: path traversal → arbitrary file write/RCE

CVE-2024-7037
6.5
EPSS 1.1%
Code ExecutionSupply ChainFrameworkPlugin
open-webuiCWE-2224 ATLAS
LOWEXPLOIT AVAIL

open-webui: filesystem enumeration via admin error messages

CVE-2024-7038
2.7
EPSS 0.3%
Data ExtractionData LeakageFrameworkInferenceRAG
open-webuiCWE-20023 ATLAS
MEDIUMEXPLOIT AVAIL

open-webui: IDOR enables cross-user memory tampering

CVE-2024-7041
6.5
EPSS 0.4%
Auth BypassModel PoisoningPrivacy ViolationAPIAgentFramework
open-webuiPatch: 0.6.3CWE-25024 ATLAS
MEDIUMEXPLOIT AVAIL

Langflow: ReDoS crashes LLM workflow backend via HTTP POST

CVE-2024-9277
6.5
EPSS 1.0%
DoSFramework
langflowCWE-13333 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