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
3,018

AI/ML CVEs Tracked

424

Critical

113

New This Week

19

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 190 results — High severity, Active exploitation, has patch
HIGH EXPLOIT AVAIL

Flyto2 Core: SSRF via unvalidated URLs in agent tools

CVE-2026-67428
8.5
EPSS 0.3%
Data Extraction Auth Bypass Agent API
flyto-core Patch: 2.26.7 CWE-918 6.2K 4 ATLAS
HIGH EXPLOIT AVAIL

Flyto2 Core: SSRF leaks LLM API keys via base_url

CVE-2026-67425
8.6
EPSS 0.3%
Data Leakage Privacy Violation Agent API
flyto-core Patch: 2.26.7 CWE-201 132 3 ATLAS
HIGH EXPLOIT AVAIL

Quarkus: HTTP auth bypass via %3B/%2F path smuggling

CVE-2026-50559
7.5
EPSS 0.5%
Auth Bypass Data Leakage API Inference
io.quarkus:quarkus-vertx-http Patch: 3.20.6.2 CWE-41 2.3K 2 ATLAS
HIGH EXPLOIT AVAIL

Pterodactyl Wings: JWT reuse enables file upload bypass

CVE-2026-54593
8.1
EPSS 0.4%
Auth Bypass Code Execution Inference
github.com/pterodactyl/wings Patch: 1.12.2 CWE-1259 492
HIGH EXPLOIT AVAIL

Pterodactyl Panel: global rate limiter enables panel-wide login DoS

CVE-2026-61609
7.5
EPSS 0.4%
DoS Framework
pterodactyl/panel Patch: 1.13.0 CWE-770 492 1 ATLAS
HIGH EXPLOIT AVAIL

Gitea: cached permission check allows repo takeover

CVE-2026-27775
8.8
EPSS 0.6%
Auth Bypass Supply Chain Training Data
code.gitea.io/gitea Patch: 1.26.3 CWE-863 6.2K 2 ATLAS
HIGH EXPLOIT AVAIL

Pillow: OOB read/DoS via unchecked mmap stride (McIdas)

CVE-2026-54058
--
EPSS 0.4%
Data Leakage DoS Inference Training Data Plugin
pillow Patch: 12.3.0 CWE-125 2 ATLAS
HIGH EXPLOIT AVAIL

Keras: unsafe pickle deserialization allows RCE

CVE-2026-12484
7.8
EPSS 0.2%
Code Execution Supply Chain Framework Model
keras Patch: 3.12.3 CWE-502 1.5K 3 ATLAS
HIGH EXPLOIT AVAIL SCANNER

SiYuan: /assets path traversal exposes API secrets

CVE-2026-54066
7.5
EPSS 1.9%
Auth Bypass Data Leakage Privacy Violation API Plugin
github.com/siyuan-note/siyuan/kernel Patch: 0.0.0-20260628153353-2d5d72223df4 CWE-22 3.0K 3 ATLAS
HIGH EXPLOIT AVAIL

Open WebUI: encoded path traversal in terminal proxy

CVE-2026-59221
7.7
EPSS 0.4%
Data Leakage Auth Bypass Framework Plugin
open-webui Patch: 0.10.0 CWE-22 4 2 ATLAS
HIGH EXPLOIT AVAIL

Open WebUI: session hijack enables cross-user code exec

CVE-2026-59216
7.7
EPSS 0.3%
Auth Bypass Code Execution Privacy Violation Agent Plugin
open-webui Patch: 0.10.0 CWE-94 4 4 ATLAS
HIGH EXPLOIT AVAIL

Open WebUI: revoked JWTs bypass WebSocket auth

CVE-2026-59219
7.1
EPSS 0.3%
Auth Bypass Data Leakage Framework API
open-webui Patch: 0.10.0 CWE-613 4 2 ATLAS
HIGH EXPLOIT AVAIL

Serena: unauth dashboard API enables RCE via memory poisoning

CVE-2026-49471
8.3
EPSS 0.3%
Auth Bypass Prompt Injection Code Execution Agent API
serena-agent Patch: 1.5.2 CWE-306 6 ATLAS
HIGH EXPLOIT AVAIL

vLLM: crafted spec-decoding request crashes GPU worker (DoS)

CVE-2026-54234
7.5
EPSS 0.4%
DoS Inference
vllm Patch: 0.24.0 CWE-20 130 2 ATLAS
HIGH EXPLOIT AVAIL

Langroid: auth bypass invokes disabled tools via raw JSON

CVE-2026-54771
8.1
EPSS 0.3%
Auth Bypass Code Execution Agent Framework
langroid Patch: 0.65.3 CWE-74 4 3 ATLAS
HIGH EXPLOIT AVAIL

Langroid: path traversal escapes sandboxed file tools

CVE-2026-50181
7.1
EPSS 0.2%
Auth Bypass Data Leakage Agent Framework
langroid Patch: 0.64.0 CWE-22 4 4 ATLAS
HIGH EXPLOIT AVAIL

Ray: RCE via pickle/torch deserialization in WebDataset

CVE-2026-57516
8.8
EPSS 0.6%
Supply Chain Code Execution Training Data Framework
ray Patch: 2.56.0 CWE-502 619 4 ATLAS
HIGH EXPLOIT AVAIL

Gogs LFS: cross-tenant object disclosure via dedupe bypass

CVE-2026-52812
--
EPSS 0.2%
Data Extraction Auth Bypass Training Data Model
gogs.io/gogs Patch: 0.14.3 CWE-345 2.9K 5 ATLAS
HIGH EXPLOIT AVAIL

Gogs: Stored XSS via .ipynb Markdown re-render bypass

CVE-2026-52798
8.9
EPSS 0.3%
Code Execution Data Extraction Supply Chain Framework API
gogs.io/gogs Patch: 0.14.3 CWE-79 3.0K 5 ATLAS
HIGH EXPLOIT AVAIL

Budibase: SSRF via DNS rebinding in automation steps

CVE-2026-54353
8.5
EPSS 0.2%
Auth Bypass Data Extraction Data Leakage Agent API
@budibase/backend-core Patch: 3.39.9 CWE-367 16 5 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