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
2,375

AI/ML CVEs Tracked

336

Critical

408

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 185 results — Critical severity, Active exploitation
Severity CVE ID Summary CVSS EPSS Package Date
CRIT E CVE-2026-53873 picklescan: blocklist bypass allows arbitrary code exec 9.8 0.5% picklescan Jun 17 CRIT E CVE-2026-3490 picklescan: blocklist bypass enables full RCE 10.0 0.6% picklescan Jun 17 CRIT E CVE-2025-71325 picklescan: scanner bypass enables RCE via model files 9.8 0.5% picklescan Jun 17 CRIT E CVE-2025-71323 picklescan: ctypes bypass enables full RCE via pickle files 9.8 0.8% picklescan Jun 17 CRIT E CVE-2025-71321 picklescan: blocklist bypass allows arbitrary file write/RCE 9.8 0.6% picklescan Jun 17 CRIT E CVE-2025-71320 picklescan: deny-list bypass enables arbitrary RCE 9.8 0.6% picklescan Jun 17 CRIT E CVE-2026-46703 Boxlite: OCI symlink traversal enables host RCE 9.6 0.5% boxlite Jun 10 CRIT E CVE-2026-46442 Flowise: sandbox escape enables authenticated RCE 9.9 0.6% flowise Jun 8 CRIT E CVE-2026-46441 Flowise: mass assignment breaks multi-tenant isolation 9.6 0.2% flowise Jun 8 CRIT E CVE-2026-46440 Flowise: plaintext auth brute-force, no rate limit 9.1 0.3% flowise Jun 8 CRIT E CVE-2026-5241 transformers: trust_remote_code bypass enables RCE via model load 9.6 0.4% transformers Jun 3 CRIT E CVE-2026-25879 langroid: Prompt-to-SQL injection enables RCE on DB host 9.8 0.7% langroid May 27 CRIT E CVE-2026-46695 Boxlite: read-only bypass enables host code execution 10.0 0.3% boxlite-cli May 21 CRIT E CVE-2026-2611 MLflow: cross-origin bypass enables RCE via AI agent 9.6 0.3% mlflow May 19 CRIT E CVE-2026-45829 ChromaDB: pre-auth RCE via trust_remote_code injection — 9.7% chromadb May 18 CRIT E CVE-2026-45311 deepseek-tui: prompt injection enables zero-approval RCE 9.6 0.4% deepseek-tui May 14 CRIT E CVE-2026-42074 openclaude: sandbox bypass allows host-level RCE — 0.4% openclaude May 12 CRIT E CVE-2026-43995 Flowise: SSRF in agent tools bypasses security wrapper 9.8 0.4% flowise May 11 CRIT E CVE-2026-44336 PraisonAI: MCP path traversal escalates to full RCE 9.6 0.5% PraisonAI May 11 CRIT E CVE-2026-44211 cline: WebSocket auth bypass enables terminal RCE 9.6 0.2% cline May 8

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