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

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

Severity CVE ID Summary CVSS EPSS Package Date

MEDI GHSA-vmhf-c436-hxj4 JupyterLab: XSS via malicious PyPI extension URL — — jupyterlab Jun 19 MEDI CVE-2026-55832 tract-onnx: path traversal exposes arbitrary local files 6.1 — tract-onnx Jun 19 MEDI CVE-2026-55414 nl-portal: GraphQL SSRF exposes Objecten-API auth token 5.3 — nl.nl-portal:form Jun 19 MEDI CVE-2026-55375 canto-saas-api: OAuth credentials logged via query params 5.3 — jleehr/canto-saas-api Jun 19 HIGH CVE-2026-49357 line-desktop-mcp: unauthenticated HTTP exposes LINE chats — 0.6% line-desktop-mcp Jun 19 MEDI CVE-2026-12706 FFmpeg RASC: UAF in decoder crashes AI inference containers 6.5 0.5% rhoai/odh-vllm-gaudi-rhel9 Jun 19 CRIT CVE-2026-12048 pgAdmin 4: Stored XSS enables full browser session hijack 9.3 0.2% — Jun 18 HIGH E CVE-2026-56078 PraisonAI: path traversal → arbitrary file read/write/RCE 8.8 0.9% PraisonAI Jun 18 MEDI CVE-2026-56077 PraisonAI: agent ID collision leaks system prompts 6.5 0.4% PraisonAI Jun 18 HIGH E CVE-2026-56076 PraisonAI: CORS bypass enables arbitrary agent execution 8.1 0.7% PraisonAI Jun 18 HIGH E CVE-2026-56075 PraisonAI: RCE via hardcoded approval_mode bypass 8.8 0.7% PraisonAI Jun 18 MEDI E CVE-2026-56074 PraisonAI: tool approval bypass enables credential theft 5.5 0.2% PraisonAI Jun 18 HIGH GHSA-fq4x-789w-jg5h agenticmail: email prompt injection → bypassPermissions RCE — — @agenticmail/openclaw Jun 18 MEDI CVE-2026-54683 nl-portal documenten-api: IDOR exposes citizen documents 6.5 — nl.nl-portal:documenten-api Jun 18 HIGH CVE-2026-46580 Eclipse Theia: workspace prompt injection enables RCE/exfil — 0.5% @theia/ai-editor Jun 18 HIGH CVE-2026-44688 Eclipse Theia: indirect prompt injection → RCE + exfil — 0.5% @theia/ai-ide Jun 18 MEDI CVE-2026-22551 @theia/ai-chat: prompt injection exfiltrates workspace secrets — 0.3% @theia/ai-ide Jun 18 UNKN CVE-2026-54003 Kirby CMS: admin takeover via reverse proxy header bypass — 0.5% getkirby/cms Jun 18 HIGH CVE-2026-54002 Kirby CMS: stored XSS bypasses DOM sanitizer via unwrap flaw — 0.4% getkirby/cms Jun 18 MEDI CVE-2026-50188 Kirby CMS: CRLF injection overrides outbound HTTP headers — 0.3% getkirby/cms Jun 18

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