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
4,331

AI/ML CVEs Tracked

535

Critical

108

New This Week

25

In CISA KEV

Sort:DateCVSSEPSSKEV firstMost exploited
Filter:AllCriticalHighMediumKEV onlyActive exploitationHas patchNo patch

Latest AI Security Threats

Showing 20 of 366 results — Critical severity, no patch
CRITICALEXPLOIT AVAIL

Flowise: unauthenticated file write enables RCE

CVE-2025-71338
10.0
EPSS 1.2%
Code ExecutionAuth BypassSupply ChainAgentFrameworkPlugin
FlowiseCWE-735 ATLAS
CRITICALEXPLOIT AVAIL

Flowise: unauthenticated RCE via Custom MCP endpoint

CVE-2025-71336
9.8
EPSS 1.1%
Code ExecutionAuth BypassAgentFramework
FlowiseCWE-786 ATLAS
CRITICALEXPLOIT AVAILSCANNER

Flowise: path traversal → RCE via missing UUID validation

CVE-2025-71334
9.8
EPSS 4.4%
Code ExecutionData ExtractionAuth BypassFrameworkAgentAPI
FlowiseCWE-734 ATLAS
CRITICALEXPLOIT AVAIL

Flowise: unauth file upload + path traversal enables RCE

CVE-2025-71333
--
EPSS 0.9%
Code ExecutionAuth BypassAgentFramework
FlowiseCWE-732 ATLAS
CRITICALEXPLOIT AVAIL

Flowise: auth bypass grants full API access

CVE-2025-71327
9.1
EPSS 0.7%
Auth BypassData ExtractionPrivacy ViolationAgentFramework
FlowiseCWE-3065 ATLAS
CRITICALEXPLOIT AVAIL

qrscp: DICOM path traversal enables arbitrary file write

CVE-2026-56445
9.1
EPSS 0.6%
Code ExecutionDoSTraining Data
CWE-222 ATLAS
CRITICAL

Gemini CLI: OS command injection enables pre-sandbox RCE

CVE-2026-12537
--
EPSS 0.2%
Code ExecutionSupply ChainAgentPlugin
run-gemini-cli GitHub Action5 ATLAS1 incident
CRITICALEXPLOIT AVAIL

picklescan: stdlib bypass enables arbitrary RCE

CVE-2026-56315
9.8
EPSS 1.1%
Supply ChainCode ExecutionFrameworkModel
picklescanCWE-18435 ATLAS
CRITICALEXPLOIT AVAIL

Flowise: RCE via MCP server command validation bypass

CVE-2026-56274
9.9
EPSS 7.5%
Code ExecutionAuth BypassAgentPlugin
Flowise6 ATLAS
CRITICAL

n8n: SSRF bypasses allowlist, exfiltrates credentials

CVE-2026-56348
9.1
EPSS 0.5%
Auth BypassData ExtractionData LeakageAgentFramework
n8nCWE-918165 ATLAS
CRITICAL

Langflow: auth bypass in MCP endpoint, CVSS 9.8

CVE-2026-7664
9.8
EPSS 0.5%
Auth BypassCode ExecutionData ExtractionFrameworkAgent
Langflow OSSCWE-2875 ATLAS
CRITICAL

Flowise: RCE and sandbox escape via overrideConfig

CVE-2024-58351
9.8
EPSS 0.7%
Code ExecutionData ExtractionDoSAgentFrameworkPlugin
FlowiseCWE-948 ATLAS
CRITICAL

pgAdmin 4: Stored XSS enables full browser session hijack

CVE-2026-12048
9.3
EPSS 0.3%
Code ExecutionData ExtractionSocial EngineeringFrameworkRAG
4 ATLAS
CRITICAL

jupyter-server: stored XSS yields kernel RCE

CVE-2026-44727
9.0
EPSS 0.4%
Code ExecutionData ExtractionAuth BypassFrameworkInference
notebookCWE-793.0K6 ATLAS
CRITICALEXPLOIT AVAIL

picklescan: scanner bypass enables pickle RCE

CVE-2026-53874
9.8
EPSS 0.5%
Supply ChainCode ExecutionModelFramework
picklescanCWE-50234 ATLAS
CRITICALEXPLOIT AVAIL

picklescan: blocklist bypass allows arbitrary code exec

CVE-2026-53873
9.8
EPSS 0.5%
Supply ChainCode ExecutionModelFramework
picklescan34 ATLAS
CRITICALEXPLOIT AVAIL

picklescan: blocklist bypass enables full RCE

CVE-2026-3490
10.0
EPSS 0.8%
Supply ChainCode ExecutionModelFramework
picklescanCWE-18335 ATLAS
CRITICALEXPLOIT AVAIL

picklescan: scanner bypass enables RCE via model files

CVE-2025-71325
9.8
EPSS 0.6%
Supply ChainCode ExecutionModelFramework
picklescan34 ATLAS
CRITICALEXPLOIT AVAIL

picklescan: ctypes bypass enables full RCE via pickle files

CVE-2025-71323
9.8
EPSS 1.0%
Supply ChainCode ExecutionFrameworkModel
picklescan35 ATLAS
CRITICALEXPLOIT AVAIL

picklescan: blocklist bypass allows arbitrary file write/RCE

CVE-2025-71321
9.8
EPSS 0.8%
Supply ChainCode ExecutionDoSFrameworkModelTraining Data
picklescan34 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