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
2,377

AI/ML CVEs Tracked

340

Critical

392

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 251 results — Active exploitation, has patch
MEDIUM EXPLOIT AVAIL

BentoML: symlink traversal exfiltrates host secrets at build

CVE-2026-40610
5.5
EPSS 0.2%
Data Extraction Supply Chain Framework
bentoml Patch: 1.4.39 CWE-59 21 4 ATLAS
CRITICAL EXPLOIT AVAIL

vm2: sandbox escape via nesting:true enables RCE

CVE-2026-44007
9.1
EPSS 0.8%
Code Execution Auth Bypass Agent Framework
vm2 Patch: 3.11.1 CWE-284 1.6K 5 ATLAS
HIGH EXPLOIT AVAIL

praisonaiagents: SSRF via URL parser confusion bypass

CVE-2026-44335
--
EPSS 0.4%
Auth Bypass Data Extraction Agent Plugin
praisonaiagents Patch: 1.6.32 CWE-918 11 4 ATLAS
HIGH EXPLOIT AVAIL

GitPython: git config injection enables hook RCE

CVE-2026-44244
7.8
EPSS 0.2%
Supply Chain Code Execution Framework
GitPython Patch: 3.1.49 CWE-94 89 3 ATLAS
MEDIUM EXPLOIT AVAIL

vLLM: speculative decoding DoS via penalty params

CVE-2026-44223
6.5
EPSS 0.4%
DoS Inference
vllm Patch: 0.20.0 CWE-131 130 2 ATLAS
HIGH EXPLOIT AVAIL

mistune: ReDoS exposes Jupyter/AI services to DoS

CVE-2026-33079
--
EPSS 0.3%
DoS Supply Chain Framework API
mistune Patch: 3.2.1 CWE-1333 1.9K 4 ATLAS
HIGH EXPLOIT AVAIL

PPTAgent: eval injection enables RCE via LLM prompt injection

CVE-2026-42079
8.6
EPSS 0.1%
Prompt Injection Code Execution Agent Framework
pptagent Patch: 1.1.36 CWE-95 5 ATLAS
CRITICAL EXPLOIT AVAIL

Langflow: path traversal allows arbitrary directory deletion

CVE-2026-42048
9.6
EPSS 0.5%
DoS Auth Bypass Framework RAG
langflow Patch: 1.9.0 CWE-22 3 ATLAS
HIGH EXPLOIT AVAIL

Jupyter Server: path traversal leaks sibling directories

CVE-2026-35397
7.1
EPSS 0.5%
Data Extraction Privacy Violation Framework
jupyter-server Patch: 2.18.0 CWE-22 1.9K 4 ATLAS
MEDIUM EXPLOIT AVAIL

jupyter-server: Open redirect enables credential phishing

CVE-2025-61669
--
EPSS 0.3%
Social Engineering Auth Bypass Framework API
jupyter-server Patch: 2.18.0 CWE-601 1.9K 5 ATLAS
HIGH EXPLOIT AVAIL

marked: infinite recursion DoS crashes Node.js via OOM

CVE-2026-41680
7.5
EPSS 0.3%
DoS Framework
marked Patch: 18.0.2 CWE-400 5.8K 4 ATLAS
MEDIUM EXPLOIT AVAIL

vllm: uninitialized KV cache memory leaks inference data

CVE-2026-7141
5.6
EPSS 0.3%
Data Leakage DoS Inference Framework
vllm Patch: 0.19.1 CWE-908 130 4 ATLAS
CRITICAL EXPLOIT AVAIL

Flowise: prompt injection → unsandboxed RCE via CSV Agent

CVE-2026-41264
9.8
EPSS 0.5%
Prompt Injection Code Execution Agent Framework
flowise-components Patch: 3.1.0 CWE-184 5 ATLAS
MEDIUM EXPLOIT AVAIL

Langflow: cleartext auth storage exposes API keys

CVE-2026-6598
4.3
EPSS 0.2%
Data Extraction Privacy Violation Framework
langflow Patch: 1.9.1 CWE-312 5 ATLAS
HIGH EXPLOIT AVAIL

Langflow: unauthenticated file upload allows RCE

CVE-2026-6596
7.3
EPSS 0.3%
Code Execution Auth Bypass Framework Agent
langflow-base Patch: 0.9.1 CWE-284 4 ATLAS
CRITICAL EXPLOIT AVAIL

Flowise: RCE via MCP stdio command injection

CVE-2026-40933
9.9
EPSS 1.9%
Code Execution Supply Chain Auth Bypass Agent Plugin Framework
flowise-components Patch: 3.1.0 CWE-78 7 ATLAS
HIGH EXPLOIT AVAIL

Keras: safe_mode bypass allows RCE via model deserialization

CVE-2026-1462
8.8
EPSS 0.4%
Supply Chain Code Execution Framework Model
keras Patch: 3.13.2 CWE-502 1.6K 4 ATLAS
MEDIUM EXPLOIT AVAIL

langsmith: prototype pollution enables auth bypass, RCE

CVE-2026-40190
5.6
EPSS 0.2%
Supply Chain Auth Bypass Code Execution Framework Agent Plugin
langsmith Patch: 0.5.18 CWE-1321 2.7K 4 ATLAS
MEDIUM EXPLOIT AVAIL

rembg: path traversal exposes arbitrary files via HTTP API

CVE-2026-40086
5.3
EPSS 0.6%
Data Extraction Privacy Violation Inference API
rembg Patch: 2.0.75 CWE-22 1.2K 4 ATLAS
HIGH EXPLOIT AVAIL

PraisonAI: unauthenticated SSRF via unvalidated webhook_url

CVE-2026-40114
7.2
EPSS 0.3%
Auth Bypass Data Extraction Privacy Violation Agent API
PraisonAI Patch: 4.5.128 CWE-918 1 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