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
2,371

AI/ML CVEs Tracked

344

Critical

449

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 249 results — Active exploitation, has patch
MEDIUM EXPLOIT AVAIL

Budibase: SSRF via VectorDB host exposes cloud metadata

CVE-2026-48148
--
EPSS 0.2%
Data Extraction Auth Bypass RAG Framework
@budibase/server Patch: 3.35.3 CWE-918 312 5 ATLAS
HIGH EXPLOIT AVAIL

Budibase: SSRF in OAuth2 exposes cloud credentials

CVE-2026-48146
7.7
EPSS 0.2%
Data Extraction Auth Bypass Agent Plugin
@budibase/server Patch: 3.39.0 CWE-918 5 ATLAS
MEDIUM EXPLOIT AVAIL

mcp-server-kubernetes: flag injection steals K8s tokens

CVE-2026-47250
6.1
EPSS 0.3%
Prompt Injection Auth Bypass Data Extraction Agent Plugin
mcp-server-kubernetes Patch: 3.7.0 CWE-88 1 6 ATLAS
HIGH EXPLOIT AVAIL

Froxlor: DNS zone injection via unsanitized TXT record

CVE-2026-41234
7.6
EPSS 0.5%
Data Extraction Supply Chain API Framework
froxlor/froxlor Patch: 2.3.7 CWE-74 479 4 ATLAS
HIGH EXPLOIT AVAIL

Froxlor: symlink-following grants customer root SSH access

CVE-2026-41236
8.8
EPSS 0.6%
Auth Bypass Code Execution Inference Framework
froxlor/froxlor Patch: 2.3.7 CWE-59 479 4 ATLAS
HIGH EXPLOIT AVAIL

Froxlor: shell whitelist bypass grants host shell access

CVE-2026-41235
--
EPSS 0.4%
Auth Bypass Code Execution API Inference
froxlor/froxlor Patch: 2.3.7 CWE-863 479 4 ATLAS
MEDIUM EXPLOIT AVAIL

local-deep-research: SSRF via URL parser differential bypass

CVE-2026-46526
5.0
EPSS 0.2%
Auth Bypass Data Extraction Agent
local-deep-research Patch: 1.6.10 CWE-918 3 ATLAS
CRITICAL EXPLOIT AVAIL

langroid: Prompt-to-SQL injection enables RCE on DB host

CVE-2026-25879
9.8
EPSS 0.7%
Prompt Injection Code Execution Data Extraction Agent Framework
langroid Patch: 0.63.0 CWE-89 4 6 ATLAS
CRITICAL EXPLOIT AVAIL

Boxlite: read-only bypass enables host code execution

CVE-2026-46695
10.0
EPSS 0.3%
Code Execution Supply Chain Data Leakage Agent Framework
boxlite-cli Patch: 0.9.0 CWE-284 4 ATLAS
HIGH EXPLOIT AVAIL

mcp-server-kubernetes: auth bypass enables full cluster RCE

CVE-2026-46519
8.8
EPSS 0.4%
Auth Bypass Code Execution Agent Plugin
mcp-server-kubernetes Patch: 3.6.0 CWE-863 1 5 ATLAS
HIGH EXPLOIT AVAIL

lmdeploy: hardcoded trust_remote_code enables RCE

CVE-2026-46432
7.8
EPSS 0.1%
Supply Chain Code Execution Inference Model Framework
lmdeploy Patch: 0.13.0 CWE-94 8.3K 5 ATLAS
MEDIUM EXPLOIT AVAIL

MLflow: missing authz exposes all model versions

CVE-2026-2734
6.5
EPSS 0.4%
Auth Bypass Data Extraction Privacy Violation Framework Model
mlflow Patch: 3.10.0 CWE-284 655 4 ATLAS
CRITICAL EXPLOIT AVAIL

MLflow: cross-origin bypass enables RCE via AI agent

CVE-2026-2611
9.6
EPSS 0.3%
Auth Bypass Code Execution Agent Framework
mlflow Patch: 3.10.0 CWE-346 655 5 ATLAS
HIGH EXPLOIT AVAIL

MLflow: insecure tmp dir perms enable model artifact RCE

CVE-2026-4137
7.0
EPSS 0.2%
Code Execution Supply Chain Framework Model
mlflow Patch: 3.11.0 CWE-378 655 4 ATLAS
HIGH EXPLOIT AVAIL

@budibase/server: SSRF in AI Extract bypasses IP blacklist

CVE-2026-45548
7.7
EPSS 0.3%
Data Extraction Auth Bypass Agent Framework
@budibase/server Patch: 3.34.8 CWE-918 5 ATLAS
HIGH EXPLOIT AVAIL

Microsoft APM: symlink attack leaks host files in agent deps

CVE-2026-45539
7.4
EPSS 0.7%
Supply Chain Data Extraction Agent Framework
apm Patch: 0.13.0 CWE-59 5 ATLAS
HIGH EXPLOIT AVAIL SCANNER

MLflow: auth bypass exposes Job API and trace injection

CVE-2026-2652
8.6
EPSS 1.3%
Auth Bypass Data Extraction Code Execution Framework Training Data
mlflow Patch: 3.11.0 CWE-305 655 4 ATLAS
CRITICAL EXPLOIT AVAIL

deepseek-tui: prompt injection enables zero-approval RCE

CVE-2026-45311
9.6
EPSS 0.4%
Prompt Injection Code Execution Data Extraction Agent Plugin
deepseek-tui Patch: 0.8.23 CWE-94 7 ATLAS
HIGH EXPLOIT AVAIL

deepseek-tui: SSRF bypass leaks cloud IAM credentials

CVE-2026-45310
7.4
EPSS 0.2%
Prompt Injection Data Extraction Auth Bypass Agent Plugin
deepseek-tui Patch: 0.8.22 CWE-918 5 ATLAS
HIGH EXPLOIT AVAIL

open-webui: code exec gate bypass via API endpoint

CVE-2026-45672
8.8
EPSS 0.4%
Auth Bypass Code Execution Framework Inference
open-webui Patch: 0.8.12 CWE-863 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