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
3,021

AI/ML CVEs Tracked

424

Critical

114

New This Week

19

In CISA KEV

Sort: Date CVSS EPSS KEV first Most exploited
Filter: All Critical High Medium KEV only Active exploitation Has patch No patch

Latest AI Security Threats

Showing 20 of 1076 results — has patch
MEDIUM

OpenClaw: auth bypass exposes restricted channel messages

CVE-2026-53815
6.5
EPSS 0.2%
Auth Bypass Data Extraction Data Leakage Agent Framework
openclaw Patch: 2026.5.19 CWE-862 4 7 ATLAS 2 incidents
HIGH

OpenClaw: privilege escalation via hook-triggered MCP scope

CVE-2026-53814
8.3
EPSS 0.3%
Auth Bypass Code Execution Agent Plugin
openclaw Patch: 2026.5.20 CWE-266 4 5 ATLAS 2 incidents
HIGH

OpenClaw: path traversal enables RCE via memory-core artifacts

CVE-2026-53813
7.8
EPSS 0.1%
Supply Chain Code Execution Data Extraction Agent Framework
openclaw Patch: 2026.4.25 CWE-427 4 6 ATLAS 1 incident
HIGH

OpenClaw: SSRF bypasses private-network access controls

CVE-2026-53812
7.7
EPSS 0.2%
Auth Bypass Data Extraction Privacy Violation Agent Plugin
openclaw Patch: 2026.5.18 CWE-918 4 5 ATLAS 1 incident
HIGH

OpenClaw: privilege escalation via identity spoofing

CVE-2026-53811
8.8
EPSS 0.3%
Auth Bypass Data Extraction Agent
openclaw Patch: 2026.5.7 CWE-290 4 7 ATLAS 1 incident
HIGH

OpenClaw: extension metadata bypass enables agent RCE

CVE-2026-53810
8.8
EPSS 0.4%
Supply Chain Code Execution Agent Plugin
openclaw Patch: 2026.5.18 CWE-829 4 9 ATLAS 1 incident
LOW

OpenClaw: policy bypass exposes restricted tool access

CVE-2026-53809
3.8
EPSS 0.1%
Auth Bypass Agent Plugin
openclaw Patch: 2026.4.25 CWE-863 4 3 ATLAS 1 incident
HIGH

OpenClaw: shell flag bypass enables RCE in agent exec

CVE-2026-53806
8.8
EPSS 0.4%
Code Execution Auth Bypass Agent Framework
openclaw Patch: 2026.5.12 CWE-367 4 4 ATLAS 1 incident
HIGH EXPLOIT AVAIL

Keras: path traversal allows arbitrary file write

CVE-2026-11816
8.1
EPSS 0.6%
Supply Chain Code Execution Framework Training Data
keras Patch: 3.14.0 CWE-22 1.6K 4 ATLAS
MEDIUM

vLLM: revision pin bypass loads unreviewed artifacts

CVE-2026-47155
6.5
EPSS 0.2%
Supply Chain Model Poisoning Inference Model Framework
vllm Patch: 0.22.0 CWE-345 130 4 ATLAS
LOW

net-imap: IMAP command smuggling enables DoS

CVE-2026-47241
--
EPSS 0.2%
DoS API
net-imap Patch: 0.6.4.1 CWE-162 313 2 ATLAS
HIGH

twig/twig: sandbox bypass leaks render context

CVE-2026-47732
--
EPSS 0.4%
Auth Bypass Data Extraction Supply Chain Framework API
twig/twig Patch: 3.26.0 CWE-20 6.3K 5 ATLAS
HIGH

skillctl: path traversal enables credential exfiltration

GHSA-wx3m-whqv-xv47
--
Supply Chain Data Extraction Privacy Violation Agent Plugin
skillctl Patch: 0.1.2 CWE-22 2 5 ATLAS
HIGH EXPLOIT AVAIL

praisonai-platform: IDOR enables cross-workspace agent read/write/delete

CVE-2026-47419
8.3
EPSS 0.3%
Auth Bypass Data Extraction Data Leakage Agent API
praisonai-platform Patch: 0.1.4 CWE-639 1 5 ATLAS
MEDIUM EXPLOIT AVAIL

mcp-server-kubernetes: flag injection steals K8s tokens

CVE-2026-47250
6.1
EPSS 0.3%
Prompt Injection Auth Bypass Data Extraction Agent Plugin
mcp-server-kubernetes Patch: 3.7.0 CWE-88 1 6 ATLAS
MEDIUM

OpenMeter: SQL injection leaks all-tenant metering data

CVE-2026-8462
--
EPSS 0.0%
Data Extraction Privacy Violation API Framework
github.com/openmeterio/openmeter Patch: 1.0.0-beta.228 CWE-89 6.3K 5 ATLAS
MEDIUM EXPLOIT AVAIL

Streamlit: weak hash enables cache integrity bypass

CVE-2026-10804
4.7
EPSS 0.1%
Supply Chain DoS Framework Inference
streamlit Patch: 1.53.1 CWE-327 3.0K 3 ATLAS
LOW EXPLOIT AVAIL

MLflow: weak dataset hash allows integrity bypass

CVE-2026-10803
3.6
EPSS 0.1%
Supply Chain Model Poisoning Framework Training Data
mlflow Patch: 3.10.1 CWE-327 680 3 ATLAS
LOW EXPLOIT AVAIL

Gradio: weak hash exposes audio cache to local users

CVE-2026-10783
2.5
EPSS 0.1%
Data Extraction Privacy Violation Framework Inference
gradio Patch: 6.15.1 CWE-327 673 3 ATLAS
HIGH

Froxlor: 2FA bypass via API grants full account access

GHSA-f9rx-7wf7-jr36
8.1
Auth Bypass Data Extraction Privacy Violation API Framework
froxlor/froxlor Patch: 2.3.7 CWE-287 499 4 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