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
3,589

AI/ML CVEs Tracked

481

Critical

94

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 1245 results — has patch
HIGH EXPLOIT AVAIL

ToolHive: containerized MCP servers can reach host services via host.docker.internal, enabling lateral movement

CVE-2026-58197
8.8
EPSS 0.4%
github.com/stacklok/toolhive Patch: 0.30.1 CWE-284 1.8K
HIGH

LMDeploy has an SSRF bypass

GHSA-39wr-7q6h-cf68
7.5
lmdeploy Patch: 0.15.0 CWE-436 1
HIGH

LMDeploy is a toolkit for compressing, deploying, and serving large language models. Versions 012.1 through 0.12.2 contain a code injection vulnerability in...

CVE-2026-33625
8.8
EPSS 0.2%
lmdeploy Patch: 0.12.3 CWE-400 1
CRITICAL

LMDeploy is a toolkit for compressing, deploying, and serving large language models. Starting in version 0.9.2 and prior to version 0.16.0, LMDeploy's PyTorch...

CVE-2025-66455
9.8
EPSS 0.7%
lmdeploy Patch: 0.16.0 CWE-502 1
HIGH EXPLOIT AVAIL

Jupyter Server is the backend for Jupyter web applications. Prior to version 2.21.0, the 5xx request logging path in jupyter_server/log.py copies the Referer...

CVE-2026-86049
7.1
EPSS 0.2%
jupyter_server Patch: 2.21.0 CWE-532 1.9K
HIGH EXPLOIT AVAIL

Grav CMS vulnerable to remote code execution via .zip file upload

CVE-2026-72819
8.8
EPSS 0.5%
getgrav/grav Patch: 2.0.13 CWE-94 505
HIGH

Grav: Incomplete callable validation in blueprint dynamic fields allows arbitrary static method invocation and file disclosure

CVE-2026-69088
8.1
EPSS 0.2%
getgrav/grav Patch: 2.0.11 CWE-94 505
HIGH

RabbitMQ amqp091-go: Plaintext Credential Exposure via Exported PLAIN Authentication Struct Fields

CVE-2026-77407
--
EPSS 0.1%
github.com/rabbitmq/amqp091-go Patch: 1.13.0 CWE-316
MEDIUM

LiteLLM is a proxy server (AI Gateway) to call LLM APIs in OpenAI (or native) format. Prior to 1.83.9, an authenticated LiteLLM Proxy caller with a valid...

CVE-2026-59823
--
EPSS 0.4%
litellm Patch: 1.83.9 CWE-918 6
MEDIUM EXPLOIT AVAIL

vLLM is an inference and serving engine for large language models. Prior to 0.28.0, request bodies for Chat Completions and Responses can set...

CVE-2026-69147
6.5
EPSS 0.5%
vllm Patch: 0.28.0 CWE-400 92
MEDIUM

vLLM is an inference and serving engine for large language models. Prior to 0.24.0, the input_audio handling path for /v1/chat/completions calls...

CVE-2026-57173
6.5
EPSS 0.7%
vllm Patch: 0.24.0 CWE-770 92
CRITICAL EXPLOIT AVAIL

LMdeploy has Remote Code Execution by Pickle Deserialization via zmq_rpc.call_and_response() in InterLM/lmdeploy

CVE-2025-59953
9.8
EPSS 0.7%
lmdeploy Patch: 0.10.2 CWE-502 1
HIGH

Mockoon: unauth admin API leaks secrets, hijacks mocks

CVE-2026-59148
8.8
EPSS 0.3%
Auth Bypass Data Leakage DoS API
@mockoon/cli Patch: 9.7.0 CWE-306 1.9K 2 ATLAS
HIGH EXPLOIT AVAIL

Traefik: HTTP routing desync enables auth/log bypass

CVE-2026-88009
--
EPSS 0.3%
Auth Bypass Data Leakage Inference API Agent
github.com/traefik/traefik/v2 Patch: 2.11.57 CWE-444 2 1 ATLAS
HIGH

mistral.rs: unbounded media fetch enables DoS

GHSA-m3wp-48jr-vr4g
7.5
DoS Inference API
mistralrs-server-core Patch: 0.8.18 CWE-400 1.2K 3 ATLAS
HIGH

mistral.rs: SSRF & file-read via image/audio URLs

GHSA-wfgq-w7cq-qj7j
7.2
Data Extraction DoS Privacy Violation Inference API
mistralrs-server-core Patch: 0.8.18 CWE-73 92 3 ATLAS
MEDIUM

Open WebUI: OAuth token exchange bypasses domain allowlist

CVE-2026-88005
6.5
EPSS 0.2%
Auth Bypass API
open-webui Patch: 0.9.0 CWE-863 3 2 ATLAS
MEDIUM

Open WebUI: OAuth endpoint skips role revocation checks

CVE-2026-88006
6.5
EPSS 0.2%
Auth Bypass Framework
open-webui Patch: 0.11.1 CWE-863 3 1 ATLAS
MEDIUM EXPLOIT AVAIL

open-webui: malicious chat history causes DoS

CVE-2026-88000
6.5
EPSS 0.3%
DoS Framework
open-webui Patch: 0.11.1 CWE-835 3 2 ATLAS
MEDIUM EXPLOIT AVAIL

Open WebUI: SSRF via redirects reaches internal/metadata IPs

CVE-2026-88001
5.0
EPSS 0.3%
Data Extraction RAG Agent Plugin
open-webui Patch: 0.11.1 CWE-918 3 2 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