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
HIGH

amqp091-go: cleartext AMQP password retained in memory

CVE-2026-77407
--
EPSS 0.1%
Data LeakageData ExtractionFrameworkAPI
github.com/rabbitmq/amqp091-goPatch: 1.13.0CWE-3162 ATLAS
MEDIUM

RAGFlow: path traversal enables arbitrary JSON file read

CVE-2026-93013
4.3
EPSS 0.5%
Data ExtractionData LeakageRAGFramework
CWE-224 ATLAS
HIGHEXPLOIT AVAIL

SiYuan: stored XSS in backlink titles enables RCE

CVE-2026-92986
8.8
EPSS 0.8%
Code ExecutionSocial EngineeringFrameworkPlugin
CWE-793 ATLAS
HIGHEXPLOIT AVAIL

SiYuan: stored XSS via bookmark labels enables RCE

CVE-2026-92985
8.8
EPSS 0.8%
Code ExecutionSocial EngineeringFramework
CWE-793 ATLAS
HIGHEXPLOIT AVAIL

LMDeploy: session leak in DistServe enables DoS via OOM

CVE-2026-92983
7.5
EPSS 0.7%
DoSInferenceFramework
lmdeployCWE-77213 ATLAS
HIGHEXPLOIT AVAIL

LMDeploy: unauthenticated assertion crash halts inference

CVE-2026-92971
7.5
EPSS 0.7%
DoSInferenceAPI
lmdeploy13 ATLAS
HIGH

Redis: cluster bus OOB read enables DoS and info leak

CVE-2026-92925
7.1
EPSS 0.7%
DoSData LeakageInferenceFramework
rhaii/vllm-rocm-rhel9942 ATLAS
MEDIUM

n8n: Source control push flaw enables cross-project deletion

CVE-2026-92588
4.4
EPSS 0.3%
Auth BypassAgentFramework
n8nCWE-639162 ATLAS
MEDIUM

n8n: Git node sandbox escape reads files outside restriction

CVE-2026-92587
5.0
EPSS 0.3%
Data ExtractionData LeakageFrameworkAgent
n8nCWE-426163 ATLAS
HIGHEXPLOIT AVAIL

LightGBM: OOB write via crafted model file in SHAP

CVE-2026-92786
7.8
EPSS 0.2%
Code ExecutionSupply ChainDoSFrameworkModel
lightgbmCWE-7871.1K4 ATLAS
HIGHEXPLOIT AVAIL

Pelican Panel: missing authz lets low-priv users run commands

CVE-2026-92762
8.8
EPSS 0.7%
Auth BypassCode ExecutionFrameworkInference
CWE-8623 ATLAS
UNKNOWN

Kedro-Datasets: unsafe torch.load enables RCE via model

CVE-2026-62997
--
EPSS 0.7%
Code ExecutionSupply ChainModel PoisoningFrameworkModelTraining Data
CWE-5025 ATLAS
MEDIUM

LiteLLM: SSRF via user_config api_base bypass

CVE-2026-59823
--
EPSS 0.4%
Auth BypassData LeakageAPIFramework
litellmPatch: 1.83.9CWE-91863 ATLAS
MEDIUMEXPLOIT AVAIL

vLLM: request-selected video backend exhausts GPU memory

CVE-2026-69147
6.5
EPSS 0.6%
DoSInferenceAPIFramework
vllmPatch: 0.28.0CWE-400943 ATLAS
MEDIUM

vLLM: unbounded audio decode causes OOM DoS

CVE-2026-57173
6.5
EPSS 0.7%
DoSInferenceAPI
vllmPatch: 0.24.0CWE-770944 ATLAS
CRITICALEXPLOIT AVAIL

LMDeploy: unsafe pickle deserialization allows RCE

CVE-2025-59953
9.8
EPSS 0.9%
Code ExecutionSupply ChainInferenceFramework
lmdeployPatch: 0.10.2CWE-50213 ATLAS
MEDIUM

vLLM: algorithmic complexity DoS in thinking budget

CVE-2026-92365
4.3
EPSS 0.5%
DoSInferenceFramework
vllmCWE-404943 ATLAS
MEDIUMEXPLOIT AVAIL

WPBot: missing capability check exposes Claude API key

CVE-2026-87959
5.4
EPSS 0.2%
Auth BypassData LeakagePluginAPI
wpbot3 ATLAS
MEDIUM

vLLM: MoRIIO KV handler flaw allows remote DoS

CVE-2026-92220
5.3
EPSS 0.7%
DoSInferenceFramework
vllmCWE-400943 ATLAS
MEDIUM

EspoCRM: weak PRNG tokens allow opt-in/invite forgery

CVE-2026-92298
4.8
EPSS 0.4%
Auth BypassPrivacy ViolationAgentAPI
2 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