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
2,390

AI/ML CVEs Tracked

342

Critical

360

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 1028 results — High severity
HIGH EXPLOIT AVAIL

langchain-core: path traversal exposes host secrets via prompt config

CVE-2026-34070
7.5
EPSS 1.1%
Data Extraction Data Leakage Framework
langchain-core Patch: 1.2.22 CWE-22 4.8K 5 ATLAS
HIGH EXPLOIT AVAIL

@mobilenext/mobile-mcp: path traversal via AI agent tool

CVE-2026-33989
8.1
EPSS 0.5%
Prompt Injection Code Execution Supply Chain Agent Plugin
@mobilenext/mobile-mcp Patch: 0.0.49 CWE-22 1 6 ATLAS
HIGH EXPLOIT AVAIL

MLflow: broken access control exposes experiment traces

CVE-2025-15381
8.1
EPSS 0.3%
Auth Bypass Data Extraction Data Leakage Framework Training Data
mlflow CWE-200 655 5 ATLAS
HIGH EXPLOIT AVAIL

Open WebUI: BOLA enables RAG poisoning via file overwrite

CVE-2026-28788
7.1
EPSS 2.9%
Auth Bypass Model Poisoning Prompt Injection RAG API Framework
open-webui Patch: 0.8.6 CWE-639 7 ATLAS
HIGH EXPLOIT AVAIL

BentoML: command injection in bentofile.yaml containerize

CVE-2026-33744
7.8
EPSS 0.3%
Code Execution Supply Chain Framework
bentoml Patch: 1.4.37 CWE-94 21 5 ATLAS
HIGH

vLLM: trust_remote_code bypass enables RCE

CVE-2026-27893
8.8
EPSS 0.7%
Code Execution Supply Chain Inference Framework Model
vllm Patch: 0.18.0 CWE-693 130 5 ATLAS
HIGH

n8n: SSH MitM enables malicious workflow injection

CVE-2026-33724
7.4
EPSS 0.3%
Supply Chain Auth Bypass Agent Framework
n8n Patch: 2.5.0 CWE-639 4 ATLAS
HIGH

n8n: SQLi in Data Table node, full DB compromise

CVE-2026-33713
8.8
EPSS 0.4%
Code Execution Data Extraction Data Leakage Agent Framework Plugin
n8n Patch: 1.123.26 CWE-89 6 ATLAS
HIGH

n8n: Prototype pollution enables RCE via workflow nodes

CVE-2026-33696
8.8
EPSS 0.8%
Code Execution Supply Chain Agent Framework Plugin
n8n Patch: 2.14.1 CWE-1321 7 ATLAS
HIGH

n8n: LDAP email match enables permanent account takeover

CVE-2026-33665
8.2
EPSS 0.3%
Auth Bypass Code Execution Data Extraction Agent Framework
n8n Patch: 2.4.0 CWE-287 5 ATLAS
HIGH EXPLOIT AVAIL

langflow: Path Traversal enables file access

CVE-2026-33497
7.5
EPSS 8.0%
Data Extraction Auth Bypass Framework Agent
langflow Patch: 1.7.1 CWE-22 5 ATLAS
HIGH EXPLOIT AVAIL

langflow: Access Control bypass enables privilege escalation

CVE-2026-33484
7.5
EPSS 5.8%
Auth Bypass Data Extraction Privacy Violation Framework API
langflow Patch: 1.9.0 CWE-284 5 ATLAS
HIGH EXPLOIT AVAIL

AI component: Input Validation flaw enables exploitation

CVE-2026-4538
7.8
EPSS 0.2%
Model Poisoning Code Execution Framework RAG Model
CWE-20 5 ATLAS
HIGH

OpenClaw: unauthenticated VNC access in AI sandbox

CVE-2026-32064
7.7
EPSS 0.5%
Auth Bypass Data Extraction Agent
OpenClaw 4 4 ATLAS 1 incident
HIGH

OpenClaw: auth bypass grants unauthorized agent control access

CVE-2026-32057
7.1
EPSS 0.3%
Auth Bypass Code Execution Agent Framework
OpenClaw 4 4 ATLAS 1 incident
HIGH

OpenClaw: RCE via shell env var injection in system.run

CVE-2026-32056
7.5
EPSS 0.6%
Code Execution Auth Bypass Supply Chain Agent Plugin Framework
OpenClaw 4 4 ATLAS 1 incident
HIGH

OpenClaw: path traversal enables arbitrary file write

CVE-2026-32055
7.6
EPSS 0.3%
Code Execution Auth Bypass Agent Framework
OpenClaw 4 4 ATLAS 1 incident
HIGH

OpenClaw: auth bypass lets operators invoke owner control-plane

CVE-2026-32051
8.8
EPSS 0.4%
Auth Bypass Code Execution Agent Framework
OpenClaw 4 5 ATLAS 2 incidents
HIGH

OpenClaw: media limit bypass enables memory exhaustion DoS

CVE-2026-32049
7.5
EPSS 0.5%
DoS Agent
OpenClaw 4 3 ATLAS
HIGH

OpenClaw: sandbox escape via cross-agent spawn bypass

CVE-2026-32048
7.5
EPSS 0.3%
Auth Bypass Code Execution Agent Framework
OpenClaw 4 4 ATLAS 1 incident

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