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
2,388

AI/ML CVEs Tracked

342

Critical

358

New This Week

18

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 1024 results — High severity
HIGH

OpenClaw versions prior to 2026.2.22 contain an allowlist bypass vulnerability in system.run that allows attackers to execute non-allowlisted commands by...

CVE-2026-28460
7.1
EPSS 0.4%
OpenClaw 4
HIGH

OpenClaw versions prior to 2026.2.22 contain an allowlist bypass vulnerability in system.run exec analysis that fails to unwrap env and shell-dispatch wrapper...

CVE-2026-27566
7.1
EPSS 0.4%
OpenClaw 4
HIGH EXPLOIT AVAIL

deepdiff: DoS causes service disruption

CVE-2026-33155
--
EPSS 0.5%
DoS Supply Chain Framework
CWE-400 4 ATLAS
HIGH

OpenClaw versions prior to 2026.3.2 contain a DNS pinning bypass vulnerability in strict URL fetch paths that allows attackers to circumvent SSRF guards when...

CVE-2026-22181
7.6
EPSS 0.2%
OpenClaw 4
HIGH

OpenClaw versions prior to 2026.2.22 in macOS node-host system.run contain an allowlist bypass vulnerability that allows remote attackers to execute...

CVE-2026-22179
7.2
EPSS 0.6%
OpenClaw 4
HIGH

OpenClaw versions prior to 2026.2.23 contain an exec approval bypass vulnerability in allowlist mode where allow-always grants could be circumvented through...

CVE-2026-22175
7.1
EPSS 0.3%
OpenClaw 4
HIGH

OpenClaw versions prior to 2026.2.19 contain a path traversal vulnerability in the Feishu media download flow where untrusted media keys are interpolated...

CVE-2026-22171
8.2
EPSS 0.3%
OpenClaw 4
HIGH

Ray Dashboard: unauthenticated path traversal file read

CVE-2026-32981
7.5
EPSS 0.7%
Data Extraction Auth Bypass Framework Inference
ray Patch: 2.8.1 CWE-22 873 4 ATLAS
HIGH EXPLOIT AVAIL

mlflow: Code Injection enables RCE

CVE-2025-14287
7.5
EPSS 1.2%
Supply Chain Model Poisoning Code Execution Framework Model
mlflow Patch: 3.8.0rc0 CWE-94 655 7 ATLAS
HIGH

libarchive: infinite loop DoS in RAR5 decompression

CVE-2026-4111
7.5
EPSS 0.7%
DoS Supply Chain Inference Framework
rhaiis/vllm-cuda-rhel9 130 4 ATLAS
HIGH EXPLOIT AVAIL

Flowise: SSRF via HTTP Node exposes internal network

CVE-2026-31829
8.8
EPSS 2.3%
Data Extraction Auth Bypass Agent Framework
flowise-components Patch: 3.0.13 CWE-918 4 ATLAS
HIGH EXPLOIT AVAIL SCANNER

mcp-atlassian: SSRF allows internal network access

CVE-2026-27826
8.2
EPSS 13.6%
Auth Bypass Prompt Injection Data Extraction Agent Plugin API
mcp-atlassian Patch: 0.17.0 CWE-918 7 ATLAS
HIGH EXPLOIT AVAIL

Flowise: header spoof auth bypass exposes admin API & creds

CVE-2026-30820
8.8
EPSS 0.5%
Auth Bypass Data Extraction Code Execution Agent Framework API
flowise CWE-863 5 ATLAS
HIGH

sagemaker: Allowlist Bypass evades input filtering

GHSA-5r2p-pjr8-7fh7
--
Code Execution Supply Chain Data Extraction Framework API
sagemaker Patch: 3.4.0 CWE-184 51 3 ATLAS
HIGH

xgrammar: security flaw enables exploitation

CVE-2026-25048
--
EPSS 0.4%
DoS Inference Framework
xgrammar Patch: 0.1.32 CWE-674 160 4 ATLAS
HIGH

langsmith: security flaw enables exploitation

CVE-2026-25750
8.1
EPSS 0.3%
Prompt Injection Data Leakage Code Execution Framework Agent API
langsmith CWE-74 2.7K 9 ATLAS
HIGH

fickling: Allowlist Bypass evades input filtering

GHSA-5hwf-rc88-82xm
--
Supply Chain Code Execution Framework Model
fickling Patch: 0.1.9 CWE-184 58 5 ATLAS
HIGH

fickling: Protection Bypass circumvents security controls

GHSA-wccx-j62j-r448
--
Code Execution Supply Chain Auth Bypass Framework Model Inference
fickling Patch: 0.1.9 CWE-693 58 5 ATLAS
HIGH

NLTK: path traversal exposes sensitive server files

CVE-2026-0847
8.6
EPSS 0.7%
Data Extraction Code Execution Supply Chain Framework
CWE-22 5 ATLAS
HIGH EXPLOIT AVAIL

bentoml: security flaw enables exploitation

CVE-2026-27905
7.8
EPSS 0.3%
Code Execution Framework Agent Model
bentoml CWE-59 21 6 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