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
3,021

AI/ML CVEs Tracked

424

Critical

113

New This Week

19

In CISA KEV

Sort: Date CVSS EPSS KEV first Most exploited
Filter: All Critical High Medium KEV only Active exploitation Has patch No patch

Latest AI Security Threats

Showing 20 of 3021 results
CRITICAL

IBM WebSphere: RCE via JAX-WS deserialization (CVSS 9.0)

CVE-2026-9319
9.0
EPSS 0.5%
Code Execution Supply Chain Data Extraction API Inference Framework
CWE-502 4 ATLAS
MEDIUM

CodexBar: session cookie leak via HTTP redirect

CVE-2026-43625
5.9
EPSS 0.2%
Data Leakage Auth Bypass Inference API
CWE-319 4 ATLAS
HIGH EXPLOIT AVAIL

F5-TTS: path traversal enables arbitrary file write

CVE-2026-43624
8.2
EPSS 0.4%
Code Execution Supply Chain Training Data Framework
CWE-22 3 ATLAS
HIGH

AnomalyMatch: RCE via torch.load() unsafe deserialization

CVE-2026-38950
7.8
EPSS 0.1%
Code Execution Supply Chain Model Framework
3 ATLAS
HIGH EXPLOIT AVAIL

Poppler: PDF integer overflow enables heap RCE

CVE-2026-10118
7.8
EPSS 0.3%
Code Execution DoS Inference
rhaiis/vllm-spyre-rhel9 130 2 ATLAS
HIGH EXPLOIT AVAIL

praisonai-platform: member can wipe entire workspace

CVE-2026-47412
8.1
EPSS 0.3%
Auth Bypass Agent Framework
praisonai-platform Patch: 0.1.4 CWE-269 1 3 ATLAS
HIGH EXPLOIT AVAIL

praisonai-platform: IDOR exposes cross-workspace tenant data

CVE-2026-47415
8.3
EPSS 0.3%
Auth Bypass Data Extraction Privacy Violation Agent Framework
praisonai-platform Patch: 0.1.4 CWE-639 1 5 ATLAS
CRITICAL EXPLOIT AVAIL

praisonai-platform: member can escalate to workspace owner

CVE-2026-47413
9.6
EPSS 0.2%
Auth Bypass Data Extraction Agent Framework
praisonai-platform Patch: 0.1.4 CWE-269 1 5 ATLAS
MEDIUM EXPLOIT AVAIL

PraisonAI: auth bypass allows workspace settings injection

CVE-2026-47411
6.5
EPSS 0.2%
Auth Bypass Data Extraction Agent API
praisonai-platform Patch: 0.1.4 CWE-269 1 4 ATLAS
HIGH EXPLOIT AVAIL

praisonai-platform: IDOR enables cross-tenant comment exfil

CVE-2026-47417
8.1
EPSS 0.2%
Auth Bypass Data Extraction Social Engineering Agent Framework
praisonai-platform Patch: 0.1.4 CWE-639 1 5 ATLAS
HIGH EXPLOIT AVAIL

praisonai-platform: IDOR exposes cross-workspace projects

CVE-2026-47418
8.1
EPSS 0.3%
Auth Bypass Data Extraction Agent Framework
praisonai-platform Patch: 0.1.4 CWE-639 1 5 ATLAS
MEDIUM EXPLOIT AVAIL

Edimax BR-6478AC: RCE via command injection in Wi-Fi handler

CVE-2026-10166
6.3
EPSS 1.1%
Code Execution Auth Bypass Inference API
4 ATLAS
MEDIUM EXPLOIT AVAIL

Edimax BR-6478AC: RCE via rootAPmac command injection

CVE-2026-10127
6.3
EPSS 1.3%
Code Execution Data Extraction Inference API
4 ATLAS
CRITICAL EXPLOIT AVAIL

praisonai-platform: member-to-owner privilege escalation

CVE-2026-47416
9.6
EPSS 0.2%
Auth Bypass Data Extraction Agent Framework
praisonai-platform Patch: 0.1.4 CWE-269 1 4 ATLAS
HIGH EXPLOIT AVAIL

praisonai-platform: auth bypass enables owner lockout

CVE-2026-47409
8.1
EPSS 0.3%
Auth Bypass Agent Framework
praisonai-platform Patch: 0.1.4 CWE-269 1 4 ATLAS
HIGH EXPLOIT AVAIL

praisonai-platform: IDOR cross-workspace label tampering

CVE-2026-47414
7.6
EPSS 0.2%
Auth Bypass Data Extraction Privacy Violation Agent Framework
praisonai-platform Patch: 0.1.4 CWE-639 1 4 ATLAS
HIGH EXPLOIT AVAIL

praisonai-platform: IDOR enables cross-workspace data poisoning

CVE-2026-47406
8.1
EPSS 0.2%
Auth Bypass Data Extraction Agent API
praisonai-platform Patch: 0.1.4 CWE-639 1 4 ATLAS
CRITICAL EXPLOIT AVAIL

praisonai-platform: hardcoded JWT → full account takeover

CVE-2026-47410
9.8
EPSS 0.4%
Auth Bypass Data Extraction Agent Framework
praisonai-platform Patch: 0.1.4 CWE-321 1 4 ATLAS
HIGH EXPLOIT AVAIL

PraisonAI Platform: member self-promotes to workspace owner

CVE-2026-47405
8.8
EPSS 0.3%
Auth Bypass Data Leakage Agent Framework
praisonai-platform Patch: 0.1.4 CWE-284 1 4 ATLAS
HIGH EXPLOIT AVAIL

praisonai-platform: IDOR breaks workspace tenant isolation

CVE-2026-47399
8.8
EPSS 0.3%
Auth Bypass Data Extraction Data Leakage Agent Framework
praisonai-platform Patch: 0.1.4 CWE-284 1 5 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