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 AVAILSCANNER

Flowise: auth bypass exposes NVIDIA NIM container endpoints

CVE-2026-30824
9.8
EPSS 37.3%
Auth BypassCode ExecutionAgentInferenceFramework
flowiseCWE-3065 ATLAS
UNKNOWNEXPLOIT AVAIL

Flowise: IDOR enables account takeover and SSO bypass

CVE-2026-30823
--
EPSS 0.5%
Auth BypassData ExtractionAgentFramework
flowiseCWE-6395 ATLAS
UNKNOWNEXPLOIT AVAIL

Flowise: mass assignment allows unauthenticated DB injection

CVE-2026-30822
--
EPSS 15.0%
Auth BypassData ExtractionCode ExecutionAgentFramework
flowiseCWE-9153 ATLAS
CRITICALEXPLOIT AVAIL

flowise: Arbitrary File Upload enables RCE

CVE-2026-30821
9.8
EPSS 16.7%
Code ExecutionFrameworkRAGPlugin
flowiseCWE-4348 ATLAS2 incidents
HIGHEXPLOIT AVAIL

Flowise: header spoof auth bypass exposes admin API & creds

CVE-2026-30820
8.8
EPSS 0.5%
Auth BypassData ExtractionCode ExecutionAgentFrameworkAPI
flowiseCWE-8635 ATLAS
MEDIUM

Greenshift: Info Disclosure leaks sensitive data

CVE-2026-2589
5.3
EPSS 0.3%
Data ExtractionData LeakageSupply ChainAPIRAGPlugin
CWE-2009 ATLAS
CRITICAL

OpenClaw: SSRF via Feishu extension exposes internal services

CVE-2026-28451
9.3
EPSS 0.3%
Prompt InjectionData ExtractionAuth BypassAgentPlugin
openclaw35 ATLAS1 incident
HIGH

sagemaker: Allowlist Bypass evades input filtering

GHSA-5r2p-pjr8-7fh7
--
Code ExecutionSupply ChainData ExtractionFrameworkAPI
sagemakerPatch: 3.4.0CWE-184503 ATLAS
CRITICAL

OpenClaw Nextcloud Talk: allowlist bypass via display name

CVE-2026-28474
9.8
EPSS 0.6%
Auth BypassSocial EngineeringAgentPlugin
nextcloud-talk33 ATLAS
MEDIUM

OpenClaw voice-call: webhook auth bypass via headers

CVE-2026-28465
5.9
EPSS 0.4%
Auth BypassSocial EngineeringPluginAgentAPI
voice-call33 ATLAS
MEDIUM

langgraph: Deserialization enables RCE

CVE-2026-28277
6.8
EPSS 5.5%
Code ExecutionData LeakageSupply ChainFrameworkAgent
langgraphPatch: 1.0.10CWE-5024.1K5 ATLAS
HIGHEXPLOIT AVAIL

xgrammar: security flaw enables exploitation

CVE-2026-25048
7.5
EPSS 1.3%
DoSInferenceFramework
xgrammarPatch: 0.1.32CWE-6741324 ATLAS
HIGH

langsmith: security flaw enables exploitation

CVE-2026-25750
8.1
EPSS 0.3%
Prompt InjectionData LeakageCode ExecutionFrameworkAgentAPI
langsmithCWE-743.2K9 ATLAS
HIGH

fickling: Allowlist Bypass evades input filtering

GHSA-5hwf-rc88-82xm
--
Supply ChainCode ExecutionFrameworkModel
ficklingPatch: 0.1.9CWE-184625 ATLAS
HIGH

fickling: Protection Bypass circumvents security controls

GHSA-wccx-j62j-r448
--
Code ExecutionSupply ChainAuth BypassFrameworkModelInference
ficklingPatch: 0.1.9CWE-693625 ATLAS
HIGHEXPLOIT AVAIL

NLTK: path traversal exposes sensitive server files

CVE-2026-0847
8.6
EPSS 1.0%
Data ExtractionCode ExecutionSupply ChainFramework
CWE-225 ATLAS
HIGHEXPLOIT AVAIL

bentoml: security flaw enables exploitation

CVE-2026-27905
7.8
EPSS 0.3%
Code ExecutionFrameworkAgentModel
bentomlCWE-59236 ATLAS
CRITICAL

picklescan: Allowlist Bypass evades input filtering

GHSA-g38g-8gr9-h9xp
9.8
Supply ChainCode ExecutionFrameworkModel
picklescanPatch: 1.0.4CWE-18437 ATLAS1 incident
CRITICAL

picklescan: security flaw enables exploitation

GHSA-vvpj-8cmc-gx39
10.0
Supply ChainCode ExecutionAuth BypassModelFramework
picklescanPatch: 1.0.4CWE-18338 ATLAS
CRITICAL

picklescan: Allowlist Bypass evades input filtering

GHSA-7wx9-6375-f5wh
9.8
Supply ChainCode ExecutionFramework
picklescanPatch: 1.0.4CWE-18435 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