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
MEDIUM

OpenClaw: pre-auth DoS in browser relay

CVE-2026-100527
5.3
EPSS 0.3%
DoSAgentPluginAPI
openclawCWE-40032 ATLAS
MEDIUM

OpenClaw Discord: media policy bypass reads local files

CVE-2026-100526
5.3
EPSS 0.3%
Data ExtractionData LeakageAgentPlugin
openclawCWE-86233 ATLAS
MEDIUM

OpenClaw: missing scope check exposes Prometheus metrics

CVE-2026-100525
4.3
EPSS 0.2%
Auth BypassData LeakageAgentPluginAPI
openclawCWE-86233 ATLAS
HIGH

OpenClaw WhatsApp: missing owner check allows account disconnect

CVE-2026-100532
8.1
EPSS 0.3%
Auth BypassDoSAgentPlugin
openclaw33 ATLAS
MEDIUM

OpenClaw Slack: authz fail-open exposes cross-channel files

CVE-2026-100531
6.5
EPSS 0.3%
Auth BypassData LeakageAgentPlugin
openclaw33 ATLAS
HIGH

LiteLLM: semantic cache tenant bypass leaks data

CVE-2026-89032
7.7
EPSS 0.3%
Data LeakageAuth BypassData ExtractionInferenceAPIAgent
litellmCWE-86365 ATLAS
MEDIUMEXPLOIT AVAIL

LangChain4j Agentic: unsafe deserialization via Jackson typing

CVE-2026-97869
4.1
EPSS 0.2%
Code ExecutionSupply ChainFrameworkAgent
2 ATLAS
HIGH

AMP for WP: stored XSS via comment regex transform

CVE-2026-83591
7.2
EPSS 0.3%
Social EngineeringData LeakagePlugin
CWE-792 ATLAS
HIGHEXPLOIT AVAIL

DBHub: readonly mode bypass enables writes and RCE

CVE-2026-61788
7.4
EPSS 0.4%
Code ExecutionAuth BypassData LeakageAgentPluginAPI
CWE-1846 ATLAS
HIGH

langchain-nvidia: local file read via VLM image paths

GHSA-g28h-2cmm-rj9x
7.5
Data ExtractionData LeakageFrameworkAPIRAG
langchain-nvidia-ai-endpointsPatch: 1.4.2CWE-223.2K4 ATLAS
HIGHEXPLOIT AVAIL

TREK: SSRF via llm_base_url exposes cloud metadata

CVE-2026-77294
8.1
EPSS 0.3%
Data LeakageAuth BypassAPIFramework
4 ATLAS
CRITICALEXPLOIT AVAIL

Decepticon: ChatML token injection yields sandbox RCE

CVE-2026-61732
10.0
EPSS 1.5%
Prompt InjectionCode ExecutionAgentFrameworkInference
decepticon-sdkPatch: 1.1.17CWE-74946 ATLAS
HIGH

rpm: command injection via %() in src.rpm filenames

CVE-2026-95521
7.8
Code ExecutionSupply ChainFrameworkInference
rhoai/odh-mlflow-operator-rhel96953 ATLAS
HIGH

rpm: macro expansion in manifest enables local code execution

CVE-2026-95519
7.8
Code ExecutionSupply ChainFrameworkInferenceTraining Data
rhoai/odh-mlflow-operator-rhel96953 ATLAS
HIGHEXPLOIT AVAIL

9router: DNS rebinding SSRF in image prefetch

CVE-2026-56676
7.4
EPSS 0.2%
Data ExtractionData LeakageInferenceAPIFramework
9routerPatch: 0.5.2CWE-3671.9K3 ATLAS
HIGH

MLflow: pickle deserialization RCE in statsmodels flavor

CVE-2026-96804
8.8
EPSS 0.7%
Code ExecutionSupply ChainModel PoisoningFrameworkModelTraining Data
mlflow6955 ATLAS
HIGH

MLflow: dspy flavor pickle control bypass enables RCE

CVE-2026-96775
8.8
EPSS 0.6%
Code ExecutionSupply ChainModel PoisoningFrameworkModel
mlflow6954 ATLAS
HIGH

Microweber admin panel: unrestricted file upload to RCE

CVE-2026-5695
--
EPSS 0.4%
Code ExecutionFramework
Administration panel5142 ATLAS
MEDIUM

OpenClaw iOS: deep-link URL logging exposes bearer keys

CVE-2026-95815
6.3
EPSS 0.2%
Data LeakageAuth BypassAgentAPI
openclawCWE-53234 ATLAS
CRITICAL

GitHub Enterprise Server: SSRF to RCE in notebook viewer

CVE-2026-77987
9.8
EPSS 0.9%
Code ExecutionData ExtractionAuth BypassFramework
3 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