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
3,590

AI/ML CVEs Tracked

481

Critical

95

New This Week

24

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 472 results — Medium severity, Active exploitation
MEDIUM EXPLOIT AVAIL

FiboSearch: unauthenticated AJAX leaks password-protected products

CVE-2026-16612
5.3
EPSS 0.3%
Auth Bypass Data Leakage Privacy Violation Plugin
MEDIUM EXPLOIT AVAIL

tract: malformed ONNX model triggers buffer flaw

CVE-2026-75093
4.3
EPSS 0.3%
Supply Chain DoS Model Inference
CWE-120 3 ATLAS
MEDIUM EXPLOIT AVAIL

MLflow: missing authZ lets users forge dataset lineage

CVE-2026-69146
6.5
EPSS 0.3%
Auth Bypass Model Poisoning Framework Training Data API
mlflow Patch: 3.15.0 CWE-862 690 2 ATLAS
MEDIUM EXPLOIT AVAIL

Transformers: path traversal via checkpoint shards

CVE-2026-75104
5.5
EPSS 0.2%
Data Leakage Supply Chain Framework Model
transformers CWE-22 9.5K 3 ATLAS
MEDIUM EXPLOIT AVAIL

vLLM: SSRF/LFI bypass in MiMo-V2 multimodal input

CVE-2026-73560
6.5
EPSS 0.3%
Data Extraction Auth Bypass Inference Model
vllm Patch: 0.26.0 CWE-918 92 3 ATLAS
MEDIUM EXPLOIT AVAIL

vLLM: integer overflow leaks other users' output

CVE-2026-73558
5.3
EPSS 0.3%
Data Leakage Privacy Violation Inference
vllm Patch: 0.27.0 CWE-190 92 3 ATLAS
MEDIUM EXPLOIT AVAIL

vLLM: ReDoS in structured output stalls engine

CVE-2026-73556
5.3
EPSS 0.3%
DoS Inference
vllm Patch: 0.26.0 CWE-400 92 3 ATLAS
MEDIUM EXPLOIT AVAIL

Flowise: unauth TTS endpoint drains stored API keys

CVE-2026-73603
--
EPSS 0.3%
Auth Bypass DoS Agent API
Flowise CWE-862 4 ATLAS
MEDIUM EXPLOIT AVAIL

SiYuan: authZ gap leaks private PDF annotations

CVE-2026-72808
5.8
EPSS 0.3%
Auth Bypass Data Leakage Privacy Violation Framework
github.com/siyuan-note/siyuan/kernel Patch: 0.0.0-20260723031702-509b35055940 CWE-862 3.1K 2 ATLAS
MEDIUM EXPLOIT AVAIL

SiYuan: broken access control exposes private docs

CVE-2026-72799
5.8
EPSS 0.2%
Data Leakage Auth Bypass Privacy Violation RAG
github.com/siyuan-note/siyuan/kernel Patch: 0.0.0-20260724112156-5bae0926b896 CWE-862 3.1K 3 ATLAS
MEDIUM EXPLOIT AVAIL

SiYuan: missing authz leaks encrypted notebook metadata

CVE-2026-72797
5.8
EPSS 0.2%
Data Leakage Auth Bypass RAG
github.com/siyuan-note/siyuan/kernel Patch: 0.0.0-20260724123622-8fb1b5766093 CWE-862 3.1K 2 ATLAS
MEDIUM EXPLOIT AVAIL

SiYuan: missing authz leaks notebook metadata

CVE-2026-72790
5.8
EPSS 0.2%
Auth Bypass Data Leakage API RAG
github.com/siyuan-note/siyuan/kernel Patch: 0.0.0-20260726005141-9edb321eb451 CWE-862 3.1K 1 ATLAS
MEDIUM EXPLOIT AVAIL

SiYuan: unauth info leak exposes admin workspace via getConf

CVE-2026-72788
5.8
EPSS 0.3%
Data Leakage Auth Bypass Privacy Violation Plugin
CWE-863 2 ATLAS
MEDIUM EXPLOIT AVAIL

Ray Enterprise Translation WP plugin: broken access control

CVE-2026-14549
4.3
EPSS 0.2%
Auth Bypass Plugin
Ray Enterprise Translation 635
MEDIUM EXPLOIT AVAIL

Ray Translation WP: Subscribers can hijack API token

CVE-2026-14548
6.5
EPSS 0.2%
Auth Bypass Plugin API
Ray Enterprise Translation 635
MEDIUM EXPLOIT AVAIL

Keras: OOM DoS via malicious .keras model load

CVE-2026-12570
5.5
EPSS 0.1%
DoS Supply Chain Framework Model
keras Patch: 3.15.0 CWE-770 1.5K 4 ATLAS
MEDIUM EXPLOIT AVAIL

openclaw-cn: symlink escape bypasses agent sandbox

CVE-2026-19008
6.3
EPSS 0.3%
Code Execution Auth Bypass Agent Plugin
CWE-59 3 ATLAS
MEDIUM EXPLOIT AVAIL

openclaw-cn: broken privilege check on elevated senders

CVE-2026-19007
6.3
EPSS 0.2%
Auth Bypass Agent
CWE-266 2 ATLAS
MEDIUM EXPLOIT AVAIL

openclaw-cn: auth bypass in bash exec approval gate

CVE-2026-19006
6.3
EPSS 0.2%
Auth Bypass Code Execution Agent
CWE-285 2 ATLAS
MEDIUM EXPLOIT AVAIL

InnoShop: path traversal in file manager deletes files

CVE-2026-18959
5.4
EPSS 0.4%
DoS Framework
1 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