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
3,595

AI/ML CVEs Tracked

482

Critical

76

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 2349 results — no patch
MEDIUM EXPLOIT AVAIL

litellm: authorization bypass exposes user list

CVE-2026-12799
4.3
EPSS 0.4%
Auth Bypass Data Extraction API Inference
litellm CWE-266 6 4 ATLAS
MEDIUM EXPLOIT AVAIL

litellm: SSRF in MCP OpenAPI spec loader endpoint

CVE-2026-12798
6.3
EPSS 0.4%
Data Extraction Auth Bypass Supply Chain Inference Agent Plugin
litellm CWE-918 6 4 ATLAS
HIGH EXPLOIT AVAIL

litellm: auth bypass in SSO debug exposes LLM proxy

CVE-2026-12795
7.3
EPSS 0.8%
Auth Bypass Data Extraction Code Execution Inference API Framework
litellm CWE-287 6 5 ATLAS
MEDIUM EXPLOIT AVAIL

litellm: auth bypass in banned keywords enterprise hook

CVE-2026-12797
6.3
EPSS 0.4%
Auth Bypass Prompt Injection Inference API Framework
litellm CWE-285 6 4 ATLAS
MEDIUM EXPLOIT AVAIL

litellm: SSO session expiration allows auth persistence

CVE-2026-12796
6.3
EPSS 0.6%
Auth Bypass Data Extraction Inference API
litellm CWE-613 6 4 ATLAS
MEDIUM EXPLOIT AVAIL

litellm: SSRF in MCP server exposes cloud metadata

CVE-2026-12774
6.3
EPSS 0.4%
Auth Bypass Data Extraction Code Execution Inference API Agent
litellm CWE-918 6 5 ATLAS
MEDIUM EXPLOIT AVAIL

litellm: session expiration bypass in proxy auth

CVE-2026-12772
6.3
EPSS 0.4%
Auth Bypass Data Extraction Inference API
litellm CWE-613 6 5 ATLAS
HIGH EXPLOIT AVAIL

litellm: JWT auth bypass in M2M proxy handler

CVE-2026-12771
7.5
EPSS 0.4%
Auth Bypass Inference API
litellm CWE-266 6 5 ATLAS
HIGH EXPLOIT AVAIL

litellm: auth bypass in Admin Key Handler endpoint

CVE-2026-12770
8.8
EPSS 0.6%
Auth Bypass DoS Inference API
litellm CWE-266 6 4 ATLAS
HIGH EXPLOIT AVAIL

vLLM: sparse tensor DoS/memory corruption via embeddings

CVE-2026-56340
7.5
EPSS 0.6%
DoS Code Execution Inference API
vllm CWE-20 92 5 ATLAS
HIGH

vLLM: ReDoS via crafted API input causes DoS

CVE-2025-71379
7.5
EPSS 0.5%
DoS Inference API
vllm CWE-1333 92 4 ATLAS
MEDIUM EXPLOIT AVAIL

picklescan: FileHandler bypass creates filesystem artifacts

CVE-2026-56304
6.5
EPSS 0.4%
Supply Chain DoS Framework Model
picklescan CWE-502 3 4 ATLAS
MEDIUM EXPLOIT AVAIL

Flowise: mass assignment enables credential hash override

CVE-2026-56276
--
EPSS 0.4%
Auth Bypass Data Extraction Agent Framework
Flowise CWE-915 5 ATLAS
MEDIUM EXPLOIT AVAIL

Flowise: PII exposure via unauthenticated password reset

CVE-2026-56267
--
EPSS 0.5%
Data Extraction Privacy Violation Agent
Flowise CWE-200 4 ATLAS
MEDIUM EXPLOIT AVAIL

Flowise: XSS enables session hijacking in AI agent UI

CVE-2025-71331
6.1
EPSS 0.3%
Auth Bypass Data Extraction Code Execution Agent Framework Plugin
Flowise CWE-80 4 ATLAS
CRITICAL

Flowise: RCE and sandbox escape via overrideConfig

CVE-2024-58351
9.8
EPSS 0.9%
Code Execution Data Extraction DoS Agent Framework Plugin
Flowise CWE-94 8 ATLAS
HIGH

mcp-searxng: SSRF via DNS rebinding in web_url_read

GHSA-mrvx-jmjw-vggc
7.1
Data Extraction Auth Bypass Agent Plugin
CWE-918 5 ATLAS
HIGH

mcp-searxng: DoS via unbounded URL response read

GHSA-xcqx-9jf5-w339
7.5
DoS Prompt Injection Agent Plugin
CWE-400 4 ATLAS
HIGH EXPLOIT AVAIL

Stanza: pickle fallback bypass enables model RCE

CVE-2026-54499
7.5
EPSS 0.5%
Supply Chain Code Execution Model Framework
torch CWE-502 25.2K 5 ATLAS
MEDIUM EXPLOIT AVAIL

Mercator: SSRF enables internal network RCE via gopher://

CVE-2026-49345
--
EPSS 0.6%
Code Execution Data Extraction API Inference
CWE-918 4 ATLAS

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