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
2,377

AI/ML CVEs Tracked

337

Critical

392

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 1551 results — no patch
Severity CVE ID Summary CVSS EPSS Package Date
MEDI CVE-2026-12799 litellm: authorization bypass exposes user list 4.3 — litellm Jun 21 MEDI CVE-2026-12798 litellm: SSRF in MCP OpenAPI spec loader endpoint 6.3 — litellm Jun 21 HIGH CVE-2026-12795 litellm: auth bypass in SSO debug exposes LLM proxy 7.3 — litellm Jun 21 MEDI CVE-2026-12797 litellm: auth bypass in banned keywords enterprise hook 6.3 — litellm Jun 21 MEDI CVE-2026-12796 litellm: SSO session expiration allows auth persistence 6.3 — litellm Jun 21 MEDI CVE-2026-12774 litellm: SSRF in MCP server exposes cloud metadata 6.3 — litellm Jun 21 MEDI CVE-2026-12772 litellm: session expiration bypass in proxy auth 6.3 — litellm Jun 21 HIGH CVE-2026-12773 litellm: auth bypass in MCP proxy, no credentials required 7.3 — litellm Jun 21 MEDI CVE-2026-12771 litellm: JWT auth bypass in M2M proxy handler 5.0 — litellm Jun 21 MEDI CVE-2026-12770 litellm: auth bypass in Admin Key Handler endpoint 5.4 — litellm Jun 21 HIGH CVE-2026-56340 vLLM: sparse tensor DoS/memory corruption via embeddings 8.8 — vllm Jun 20 MEDI CVE-2025-71379 vLLM: ReDoS via crafted API input causes DoS 4.3 — vllm Jun 20 MEDI CVE-2026-56304 picklescan: FileHandler bypass creates filesystem artifacts 6.5 — picklescan Jun 20 MEDI CVE-2026-56276 Flowise: mass assignment enables credential hash override — — Flowise Jun 20 MEDI CVE-2026-56267 Flowise: PII exposure via unauthenticated password reset — — Flowise Jun 20 MEDI E CVE-2025-71331 Flowise: XSS enables session hijacking in AI agent UI 6.1 — Flowise Jun 20 CRIT CVE-2024-58351 Flowise: RCE and sandbox escape via overrideConfig 9.8 — Flowise Jun 20 HIGH GHSA-mrvx-jmjw-vggc mcp-searxng: SSRF via DNS rebinding in web_url_read 7.1 — — Jun 19 HIGH GHSA-xcqx-9jf5-w339 mcp-searxng: DoS via unbounded URL response read 7.5 — — Jun 19 HIGH CVE-2026-54499 Stanza: pickle fallback bypass enables model RCE 7.5 — torch Jun 19

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