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
3,590

AI/ML CVEs Tracked

481

Critical

95

New This Week

24

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 1661 results — Active exploitation
Severity CVE ID Summary CVSS EPSS Package Date
HIGH E CVE-2026-69148 MLflow: missing authz check leaks private artifacts 7.1 0.3% mlflow Aug 17 MEDI E CVE-2026-69146 MLflow: missing authZ lets users forge dataset lineage 6.5 0.3% mlflow Aug 17 CRIT CVE-2026-64849 MLflow: unauth SSRF via webhook hits cloud metadata 9.3 16.4% mlflow Aug 17 MEDI E CVE-2026-75104 Transformers: path traversal via checkpoint shards 5.5 0.2% transformers Aug 17 MEDI E CVE-2026-73560 vLLM: SSRF/LFI bypass in MiMo-V2 multimodal input 6.5 0.3% vllm Aug 17 HIGH E CVE-2026-35219 Budibase: SSRF in automations reaches cloud metadata — 0.3% — Aug 17 HIGH E CVE-2026-74868 SiYuan: unthrottled brute-force exposes published notes 7.5 0.4% — Aug 17 HIGH E CVE-2026-19960 Edimax EW-7478APC: command injection via rootAPmac 7.4 1.2% — Aug 16 HIGH E CVE-2026-73045 SiYuan: brute-force bypass of notebook publish passwords 7.5 0.3% — Aug 15 MEDI E CVE-2026-73558 vLLM: integer overflow leaks other users' output 5.3 0.3% vllm Aug 13 MEDI E CVE-2026-73556 vLLM: ReDoS in structured output stalls engine 5.3 0.3% vllm Aug 13 HIGH E CVE-2026-73608 SiYuan: missing authz exposes filtered DB rows 8.6 0.2% — Aug 13 MEDI E CVE-2026-73603 Flowise: unauth TTS endpoint drains stored API keys — 0.3% Flowise Aug 13 CRIT E CVE-2026-73601 Flowise: RCE via Custom MCP node env var injection — 0.9% Flowise Aug 13 UNKN E CVE-2026-73488 Flowise: IDOR exposes cross-tenant billing/PII data — 0.3% Flowise Aug 13 CRIT E CVE-2026-73487 Flowise: Python sandbox bypass enables unauth RCE — 1.0% Flowise Aug 13 UNKN E CVE-2026-73486 Flowise: CSV Agent code injection enables RCE — 0.7% Flowise Aug 13 UNKN E CVE-2026-73484 Flowise: Pandas sandbox bypass leaks files, writes to disk — 0.4% Flowise Aug 13 CRIT E CVE-2026-73483 Flowise: sandbox escape via puppeteer.launch() to RCE — 0.6% Flowise Aug 13 MEDI E CVE-2026-72808 SiYuan: authZ gap leaks private PDF annotations 5.8 0.3% github.com/siyuan-note/siyuan/kernel Aug 12

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