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
3,591

AI/ML CVEs Tracked

481

Critical

96

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 2346 results — no patch
Severity CVE ID Summary CVSS EPSS Package Date
HIGH CVE-2026-18899 Langflow: path traversal enables arbitrary file read 7.5 0.5% langflow Aug 28 HIGH CVE-2026-18891 Langflow: broken auth allows unauthorized flow execution 8.2 0.3% langflow Aug 28 HIGH E CVE-2026-18729 Langflow: authenticated RCE via unsafe code generation 8.8 0.9% langflow Aug 28 MEDI CVE-2026-18545 Langflow: SSRF lets authenticated users probe internal network 4.3 0.2% langflow Aug 28 MEDI E CVE-2026-82290 Chainlit: IDOR lets users tamper with others' feedback 5.3 0.2% chainlit Aug 28 HIGH E CVE-2026-82288 SD WebUI: cmd-flags endpoint leaks creds cleartext 7.5 0.3% — Aug 28 HIGH E CVE-2026-82275 Qwen-Agent: path traversal in doc parser leaks files 7.5 0.4% — Aug 28 HIGH E CVE-2026-82268 Qwen-Agent: unauth SSRF via document URL parser 7.5 0.3% — Aug 28 HIGH CVE-2026-37237 vLLM: unbounded media URLs cause memory-exhaustion DoS 7.5 0.5% vllm Aug 28 MEDI CVE-2026-18393 FFmpeg: heap overflow via crafted TDSC cursor in video 5.4 0.3% rhoai/odh-vllm-gaudi-rhel9 Aug 28 LOW E CVE-2026-81836 Roo-Code: cleartext OAuth callback leaks auth tokens 3.7 0.2% — Aug 27 MEDI E CVE-2026-37009 crewai-tools: SQLi in NL2SQLTool allows DB compromise 6.5 0.3% — Aug 27 CRIT E CVE-2026-37007 crewai-tools: Path traversal in FileWriterTool enables RCE 9.8 0.7% — Aug 27 HIGH CVE-2026-47852 Spring AI: predictable ONNX cache path enables model swap 7.5 0.2% — Aug 27 MEDI CVE-2026-37067 Veno File Manager: unauth log disclosure via broken ACL 5.3 0.2% — Aug 27 UNKN CVE-2026-69129 KubePi: broken cluster-scope check exposes MLOps clusters — 0.2% — Aug 26 UNKN CVE-2026-65956 KubePi: exposed SSO config API enables takeover — 0.4% — Aug 26 HIGH E CVE-2026-47665 Penpot: stored XSS in comments enables session takeover 8.7 0.3% — Aug 26 HIGH E CVE-2026-61617 Pterodactyl Wings: SFTP quota bypass causes node-wide DoS 7.7 0.2% — Aug 26 CRIT E CVE-2025-61165 Cohere North AI: file upload flaw enables RCE 9.8 0.4% — Aug 26

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