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
3,021

AI/ML CVEs Tracked

424

Critical

114

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 3021 results
MEDIUM

JupyterLab: XSS via malicious PyPI extension URL

GHSA-vmhf-c436-hxj4
--
Supply Chain Code Execution Social Engineering Plugin Framework
jupyterlab Patch: 4.5.9 CWE-84 1.9K 5 ATLAS
MEDIUM

tract-onnx: path traversal exposes arbitrary local files

CVE-2026-55832
6.1
Supply Chain Data Extraction Model Inference
tract-onnx Patch: 0.21.17 CWE-22 1.1K 4 ATLAS
MEDIUM

nl-portal: GraphQL SSRF exposes Objecten-API auth token

CVE-2026-55414
5.3
Auth Bypass Data Extraction Privacy Violation API Framework
nl.nl-portal:form Patch: 3.0.4 CWE-862 620 3 ATLAS
MEDIUM

canto-saas-api: OAuth credentials logged via query params

CVE-2026-55375
5.3
Data Extraction Auth Bypass API
jleehr/canto-saas-api Patch: 3.0.0 CWE-209 3 ATLAS
HIGH

line-desktop-mcp: unauthenticated HTTP exposes LINE chats

CVE-2026-49357
--
EPSS 0.6%
Auth Bypass Data Extraction Privacy Violation Agent Plugin
line-desktop-mcp Patch: 1.1.2 CWE-306 16 6 ATLAS
MEDIUM

FFmpeg RASC: UAF in decoder crashes AI inference containers

CVE-2026-12706
6.5
EPSS 0.5%
DoS Supply Chain Inference Framework
rhoai/odh-vllm-gaudi-rhel9 130 3 ATLAS
CRITICAL

pgAdmin 4: Stored XSS enables full browser session hijack

CVE-2026-12048
9.3
EPSS 0.2%
Code Execution Data Extraction Social Engineering Framework RAG
4 ATLAS
HIGH EXPLOIT AVAIL

PraisonAI: path traversal → arbitrary file read/write/RCE

CVE-2026-56078
8.8
EPSS 0.9%
Code Execution Data Extraction Auth Bypass Agent Framework
PraisonAI CWE-22 1 6 ATLAS
MEDIUM

PraisonAI: agent ID collision leaks system prompts

CVE-2026-56077
6.5
EPSS 0.4%
Data Leakage Data Extraction Privacy Violation Agent Framework
PraisonAI CWE-668 1 5 ATLAS
HIGH EXPLOIT AVAIL

PraisonAI: CORS bypass enables arbitrary agent execution

CVE-2026-56076
8.1
EPSS 0.7%
Auth Bypass Data Extraction Code Execution Agent API Framework
PraisonAI CWE-942 1 6 ATLAS
HIGH EXPLOIT AVAIL

PraisonAI: RCE via hardcoded approval_mode bypass

CVE-2026-56075
8.8
EPSS 0.7%
Code Execution Auth Bypass Agent Framework
PraisonAI CWE-863 1 5 ATLAS
MEDIUM EXPLOIT AVAIL

PraisonAI: tool approval bypass enables credential theft

CVE-2026-56074
5.5
EPSS 0.2%
Auth Bypass Data Extraction Agent Plugin
PraisonAI CWE-863 1 5 ATLAS
HIGH

agenticmail: email prompt injection → bypassPermissions RCE

GHSA-fq4x-789w-jg5h
--
Prompt Injection Code Execution Auth Bypass Agent Framework API
@agenticmail/openclaw Patch: 0.5.71 CWE-306 4 6 ATLAS
MEDIUM

nl-portal documenten-api: IDOR exposes citizen documents

CVE-2026-54683
6.5
Auth Bypass Data Extraction Privacy Violation API
nl.nl-portal:documenten-api Patch: 3.0.3 CWE-285 620 3 ATLAS
HIGH

Eclipse Theia: workspace prompt injection enables RCE/exfil

CVE-2026-46580
--
EPSS 0.5%
Prompt Injection Code Execution Data Extraction Agent Framework Plugin
@theia/ai-editor Patch: 1.71.0 CWE-829 7 ATLAS
HIGH

Eclipse Theia: indirect prompt injection → RCE + exfil

CVE-2026-44688
--
EPSS 0.5%
Prompt Injection Data Extraction Code Execution Agent Framework
@theia/ai-ide Patch: 1.71.0 CWE-829 6 ATLAS
MEDIUM

@theia/ai-chat: prompt injection exfiltrates workspace secrets

CVE-2026-22551
--
EPSS 0.3%
Prompt Injection Data Extraction Data Leakage Agent Framework Plugin
@theia/ai-ide Patch: 1.71.0 CWE-201 4 ATLAS
UNKNOWN

Kirby CMS: admin takeover via reverse proxy header bypass

CVE-2026-54003
--
EPSS 0.5%
Auth Bypass Code Execution API Framework
getkirby/cms Patch: 4.9.4 CWE-454 499 3 ATLAS
HIGH

Kirby CMS: stored XSS bypasses DOM sanitizer via unwrap flaw

CVE-2026-54002
--
EPSS 0.4%
Code Execution Data Extraction Auth Bypass Plugin API
getkirby/cms Patch: 4.9.4 CWE-79 499 4 ATLAS
MEDIUM

Kirby CMS: CRLF injection overrides outbound HTTP headers

CVE-2026-50188
--
EPSS 0.3%
Auth Bypass Data Leakage Plugin API
getkirby/cms Patch: 4.9.4 CWE-93 499 4 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