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
4,307

AI/ML CVEs Tracked

533

Critical

96

New This Week

25

In CISA KEV

Sort:DateCVSSEPSSKEV firstMost exploited
Filter:AllCriticalHighMediumKEV onlyActive exploitationHas patchNo patch

Latest AI Security Threats

Showing 20 of 943 results — High severity, Active exploitation
HIGHEXPLOIT AVAIL

Flyto2 Core: SSRF via unvalidated URLs in agent tools

CVE-2026-67428
8.5
EPSS 0.4%
Data ExtractionAuth BypassAgentAPI
flyto-corePatch: 2.26.7CWE-9186.3K4 ATLAS
HIGHEXPLOIT AVAIL

Flyto2 Core: SSRF leaks LLM API keys via base_url

CVE-2026-67425
8.6
EPSS 0.4%
Data LeakagePrivacy ViolationAgentAPI
flyto-corePatch: 2.26.7CWE-2011.8K3 ATLAS
HIGHEXPLOIT AVAIL

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

CVE-2026-50559
7.5
EPSS 1.0%
Auth BypassData LeakageAPIInference
io.quarkus:quarkus-vertx-httpPatch: 3.20.6.2CWE-412.6K2 ATLAS
HIGHEXPLOIT AVAIL

Pterodactyl Wings: JWT reuse enables file upload bypass

CVE-2026-54593
8.1
EPSS 0.7%
Auth BypassCode ExecutionInference
github.com/pterodactyl/wingsPatch: 1.12.2CWE-1259514
HIGHEXPLOIT AVAIL

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

CVE-2026-61609
7.5
EPSS 0.5%
DoSFramework
pterodactyl/panelPatch: 1.13.0CWE-7705141 ATLAS
HIGHEXPLOIT AVAIL

Open WebUI: broken authz lets users overwrite channel chats

CVE-2026-59714
7.1
EPSS 0.5%
Auth BypassSocial EngineeringFrameworkAPI
open-webuiPatch: 0.10.0CWE-86222 ATLAS
HIGHEXPLOIT AVAIL

CyberPanel: IDOR exposes cross-tenant backups

CVE-2026-65917
8.8
EPSS 0.5%
Auth BypassData LeakageDoSAPI
CWE-6391 ATLAS
HIGHEXPLOIT AVAIL

Ollama: crafted GGUF file crashes inference server

CVE-2026-65315
7.5
EPSS 0.8%
DoSInferenceModel
ollamaCWE-7891.9K2 ATLAS
HIGHEXPLOIT AVAIL

Gitea: cached permission check allows repo takeover

CVE-2026-27775
8.8
EPSS 0.9%
Auth BypassSupply ChainTraining Data
code.gitea.io/giteaPatch: 1.26.3CWE-8636.3K2 ATLAS
HIGHEXPLOIT AVAIL

lmdeploy: SSRF via redirect bypasses private IP guard

CVE-2026-63764
8.6
EPSS 0.5%
Auth BypassData LeakageAPIInference
lmdeployCWE-91812 ATLAS
HIGHEXPLOIT AVAIL

Kubeflow: token theft lets any user hijack accounts

CVE-2026-47237
8.0
EPSS 0.4%
Auth BypassData LeakageFrameworkAPI
CWE-2663 ATLAS
HIGHEXPLOIT AVAIL

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

CVE-2026-54058
--
EPSS 0.5%
Data LeakageDoSInferenceTraining DataPlugin
pillowPatch: 12.3.0CWE-1252 ATLAS
HIGHEXPLOIT AVAIL

Keras: unsafe pickle deserialization allows RCE

CVE-2026-12484
7.8
EPSS 0.3%
Code ExecutionSupply ChainFrameworkModel
kerasPatch: 3.12.3CWE-5024.1K3 ATLAS
HIGHEXPLOIT AVAIL

xdgmime: heap overflow in magic file parsing

CVE-2026-16118
7.1
EPSS 0.3%
DoSCode ExecutionInferenceFramework
rhaiis/vllm-cuda-rhel9942 ATLAS
HIGHEXPLOIT AVAIL

TGI: SSRF via image_url exposes cloud metadata creds

CVE-2026-63086
8.6
EPSS 0.4%
Data ExtractionAuth BypassInferenceAPI
text-generation-inferenceCWE-9184 ATLAS
HIGHEXPLOIT AVAIL

PyTorch Lightning: RCE via malicious checkpoint files

CVE-2026-58659
7.8
EPSS 0.6%
Code ExecutionSupply ChainFrameworkModel
pytorch-lightningCWE-4701.7K4 ATLAS
HIGHEXPLOIT AVAIL

PraisonAI: RCE via unsigned plugin auto-load

CVE-2026-61446
8.4
EPSS 0.3%
Supply ChainCode ExecutionAgentPlugin
PraisonAICWE-9414 ATLAS
HIGHEXPLOIT AVAIL

PraisonAI: path traversal leads to RCE via SkillTools

CVE-2026-61443
8.1
EPSS 0.6%
Code ExecutionData LeakageAgentPlugin
PraisonAICWE-2214 ATLAS
HIGHEXPLOIT AVAIL

PraisonAI: RCE via broken AST sandbox in workflows

CVE-2026-61438
7.3
EPSS 0.3%
Code ExecutionSupply ChainAgentPlugin
PraisonAICWE-7814 ATLAS
HIGHEXPLOIT AVAIL

PraisonAI: missing webhook signature check spoofs agents

CVE-2026-61436
8.6
EPSS 0.4%
Auth BypassSocial EngineeringAgentAPI
PraisonAICWE-28714 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