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 565 results — Medium severity, Active exploitation
MEDIUMEXPLOIT AVAIL

Keras: path traversal via layer names allows arbitrary file write

CVE-2026-12479
6.1
EPSS 0.4%
Supply ChainCode ExecutionFrameworkModel
kerasPatch: 3.12.3CWE-224.1K4 ATLAS
MEDIUMEXPLOIT AVAIL

Langflow: code injection via Bundle URL Loader (PoC)

CVE-2026-12822
5.3
EPSS 0.3%
Code ExecutionData ExtractionFrameworkAgent
langflowCWE-744 ATLAS
MEDIUMEXPLOIT AVAIL

Flowise: path traversal in S3 loader exposes documents

CVE-2026-12821
6.3
EPSS 0.5%
Data ExtractionData LeakageAgentRAGFramework
FlowiseCWE-225 ATLAS
MEDIUMEXPLOIT AVAIL

Craft CMS: stored XSS hijacks admin panel sessions

CVE-2026-56393
4.8
EPSS 0.2%
Code ExecutionData ExtractionAuth BypassFrameworkPlugin
4 ATLAS
MEDIUMEXPLOIT AVAIL

litellm: authorization bypass exposes user list

CVE-2026-12799
4.3
EPSS 0.4%
Auth BypassData ExtractionAPIInference
litellmCWE-26664 ATLAS
MEDIUMEXPLOIT AVAIL

litellm: SSRF in MCP OpenAPI spec loader endpoint

CVE-2026-12798
6.3
EPSS 0.4%
Data ExtractionAuth BypassSupply ChainInferenceAgentPlugin
litellmCWE-91864 ATLAS
MEDIUMEXPLOIT AVAIL

litellm: auth bypass in banned keywords enterprise hook

CVE-2026-12797
6.3
EPSS 0.4%
Auth BypassPrompt InjectionInferenceAPIFramework
litellmCWE-28564 ATLAS
MEDIUMEXPLOIT AVAIL

litellm: SSO session expiration allows auth persistence

CVE-2026-12796
6.3
EPSS 0.6%
Auth BypassData ExtractionInferenceAPI
litellmCWE-61364 ATLAS
MEDIUMEXPLOIT AVAIL

litellm: SSRF in MCP server exposes cloud metadata

CVE-2026-12774
6.3
EPSS 0.4%
Auth BypassData ExtractionCode ExecutionInferenceAPIAgent
litellmCWE-91865 ATLAS
MEDIUMEXPLOIT AVAIL

litellm: session expiration bypass in proxy auth

CVE-2026-12772
6.3
EPSS 0.4%
Auth BypassData ExtractionInferenceAPI
litellmCWE-61365 ATLAS
MEDIUMEXPLOIT AVAIL

picklescan: FileHandler bypass creates filesystem artifacts

CVE-2026-56304
6.5
EPSS 0.4%
Supply ChainDoSFrameworkModel
picklescanCWE-50234 ATLAS
MEDIUMEXPLOIT AVAIL

Flowise: mass assignment enables credential hash override

CVE-2026-56276
--
EPSS 0.4%
Auth BypassData ExtractionAgentFramework
FlowiseCWE-9155 ATLAS
MEDIUMEXPLOIT AVAIL

Flowise: PII exposure via unauthenticated password reset

CVE-2026-56267
--
EPSS 0.5%
Data ExtractionPrivacy ViolationAgent
FlowiseCWE-2004 ATLAS
MEDIUMEXPLOIT AVAIL

Flowise: XSS enables session hijacking in AI agent UI

CVE-2025-71331
6.1
EPSS 0.3%
Auth BypassData ExtractionCode ExecutionAgentFrameworkPlugin
FlowiseCWE-804 ATLAS
MEDIUMEXPLOIT AVAIL

Langflow: logout fails to clear session tokens

CVE-2026-55423
6.1
EPSS 0.2%
Auth BypassData ExtractionFrameworkAgent
langflowPatch: 1.7.0CWE-6133 ATLAS
MEDIUMEXPLOIT AVAIL

Mercator: SSRF enables internal network RCE via gopher://

CVE-2026-49345
--
EPSS 0.6%
Code ExecutionData ExtractionAPIInference
CWE-9184 ATLAS
MEDIUMEXPLOIT AVAIL

tract-onnx: path traversal exposes arbitrary local files

CVE-2026-55832
6.1
EPSS 0.2%
Supply ChainData ExtractionModelInference
tract-onnxPatch: 0.21.17CWE-221.1K4 ATLAS
MEDIUMEXPLOIT AVAIL

nl-portal: GraphQL SSRF exposes Objecten-API auth token

CVE-2026-55414
5.3
EPSS 0.4%
Auth BypassData ExtractionPrivacy ViolationAPIFramework
nl.nl-portal:formPatch: 3.0.4CWE-8626423 ATLAS
MEDIUMEXPLOIT AVAIL

PraisonAI: agent ID collision leaks system prompts

CVE-2026-56077
6.5
EPSS 0.4%
Data LeakageData ExtractionPrivacy ViolationAgentFramework
PraisonAICWE-66815 ATLAS
MEDIUMEXPLOIT AVAIL

PraisonAI: tool approval bypass enables credential theft

CVE-2026-56074
5.5
EPSS 0.2%
Auth BypassData ExtractionAgentPlugin
PraisonAICWE-86315 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