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 616 results — High severity, has patch
HIGHEXPLOIT AVAIL

Open WebUI: iframe sandbox bypass = account takeover

CVE-2026-70486
8.2
EPSS 0.4%
Code ExecutionData LeakageAuth BypassAgentFramework
open-webuiPatch: 0.11.0CWE-7924 ATLAS
HIGHEXPLOIT AVAIL

Open WebUI: NAT64 IPv6 trick bypasses SSRF filter, leaks metadata

CVE-2026-70485
7.1
EPSS 0.4%
Data ExtractionPrivacy ViolationRAGAPI
open-webuiPatch: 0.11.0CWE-91823 ATLAS
HIGHEXPLOIT AVAIL

Open WebUI: OAuth token exchange enables takeover

CVE-2026-70482
8.1
EPSS 0.6%
Auth BypassPrivacy ViolationFrameworkAPI
open-webuiPatch: 0.11.0CWE-28723 ATLAS
HIGHEXPLOIT AVAIL

Open WebUI: Playwright SSRF leaks cloud metadata

CVE-2026-70479
7.7
EPSS 0.5%
Data LeakageAuth BypassRAGFramework
open-webuiPatch: 0.11.0CWE-91823 ATLAS
HIGHEXPLOIT AVAIL

Flowise: missing workspace auth in OAuth2 credential routes

CVE-2026-70474
--
EPSS 0.5%
Auth BypassData LeakageFrameworkAgentAPI
flowisePatch: 3.1.3CWE-8634 ATLAS
HIGHEXPLOIT AVAIL

Flowise: broken auth exposes cross-tenant OpenAI keys

CVE-2026-70472
--
EPSS 0.5%
Auth BypassData LeakageAgentRAGAPI
flowisePatch: 3.1.3CWE-2854 ATLAS
HIGH

Flowise: S3 loader path traversal enables file write

GHSA-88pr-878c-24wf
--
Code ExecutionDoSAgentPluginRAG
flowisePatch: 3.1.3CWE-223 ATLAS
HIGHEXPLOIT AVAIL

Flowise: broken authz allows cross-type flow deletion

CVE-2026-69262
--
EPSS 0.5%
Auth BypassDoSAgentFramework
flowisePatch: 3.1.3CWE-8631 ATLAS
HIGHEXPLOIT AVAIL

Flowise: unauth overrideConfig injects flow session state

CVE-2026-69258
--
EPSS 0.7%
Auth BypassPrompt InjectionAgentFramework
flowisePatch: 3.1.3CWE-6394 ATLAS
HIGHEXPLOIT AVAIL

cryptography: exponential DoS in cert chain validation

CVE-2026-69249
--
EPSS 0.3%
DoSAPIAgentFramework
cryptographyPatch: 49.0.0CWE-4001.8K3 ATLAS
HIGH

transformers: path traversal in save_pretrained() writes files

CVE-2026-9856
7.1
EPSS 0.5%
Supply ChainCode ExecutionFrameworkModel
transformersPatch: 5.10.0CWE-229.8K5 ATLAS
HIGH

Dynatrace MCP server: unauth HTTP data exfil via DQL

GHSA-p7w7-4929-vpj5
7.5
Auth BypassData LeakageData ExtractionAgentPluginAPI
@dynatrace-oss/dynatrace-mcp-serverPatch: 2.0.0CWE-3063.0K3 ATLAS
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
HIGH

etcd: Watch API auth bypass leaks entire keyspace

GHSA-xg4h-6gfc-h4m8
--
Auth BypassData LeakageFrameworkAPI
go.etcd.io/etcd/v3Patch: 3.7.1CWE-8636.3K3 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
HIGH

JupyterLab: crafted settings file executes code

GHSA-pppj-hq3g-57pj
--
Code ExecutionSocial EngineeringFramework
jupyterlabPatch: 4.6.2CWE-1161.9K3 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