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
3,021

AI/ML CVEs Tracked

424

Critical

114

New This Week

19

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 859 results — High severity, no patch
HIGH

vLLM: sparse tensor DoS/memory corruption via embeddings

CVE-2026-56340
7.5
EPSS 0.4%
DoS Code Execution Inference API
vllm CWE-20 130 5 ATLAS
HIGH

vLLM: ReDoS via crafted API input causes DoS

CVE-2025-71379
7.5
EPSS 0.3%
DoS Inference API
vllm CWE-1333 130 4 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 0.3%
Supply Chain Code Execution Model Framework
torch CWE-502 24.4K 5 ATLAS
HIGH EXPLOIT AVAIL

libaom: AV1 SVC OOB write enables RCE

CVE-2026-56211
7.1
EPSS 0.5%
Code Execution Supply Chain Inference
rhaiis/vllm-cpu-rhel9 130 2 ATLAS
HIGH

libaom: AV1 SVC bounds-check miss leaks heap, crashes

CVE-2026-56210
7.1
EPSS 0.3%
DoS Data Leakage Supply Chain Inference Framework
rhaiis/vllm-cpu-rhel9 130 3 ATLAS
HIGH

libaom: heap overflow in AV1 encoder LAP mode

CVE-2026-56208
7.6
EPSS 0.3%
Code Execution DoS Inference
rhaiis/vllm-cpu-rhel9 130 2 ATLAS
HIGH

libaom: arbitrary address write in AV1 SVC codec

CVE-2026-56209
7.1
EPSS 0.3%
Code Execution DoS Supply Chain Inference Training Data Framework
rhaiis/vllm-cpu-rhel9 130 3 ATLAS
HIGH

agentic-flow: MCP tool args enable OS command injection RCE

GHSA-vcv2-r9jh-99m5
8.8
Code Execution Supply Chain Agent Plugin
CWE-78 5 ATLAS
HIGH EXPLOIT AVAIL

PraisonAI: path traversal → arbitrary file read/write/RCE

CVE-2026-56078
8.8
EPSS 0.9%
Code Execution Data Extraction Auth Bypass Agent Framework
PraisonAI CWE-22 1 6 ATLAS
HIGH EXPLOIT AVAIL

PraisonAI: CORS bypass enables arbitrary agent execution

CVE-2026-56076
8.1
EPSS 0.7%
Auth Bypass Data Extraction Code Execution Agent API Framework
PraisonAI CWE-942 1 6 ATLAS
HIGH EXPLOIT AVAIL

PraisonAI: RCE via hardcoded approval_mode bypass

CVE-2026-56075
8.8
EPSS 0.7%
Code Execution Auth Bypass Agent Framework
PraisonAI CWE-863 1 5 ATLAS
HIGH

PraisonAI: sandbox escape via silent Landlock fallback

GHSA-6jcq-6546-qrrw
8.8
Code Execution Data Extraction Auth Bypass Agent Framework
praisonaiagents CWE-668 20 5 ATLAS
HIGH

PraisonAI: workflow policy bypass enables shell RCE

GHSA-7qw2-w5rc-37x2
7.8
Auth Bypass Code Execution Agent Framework
praisonaiagents CWE-78 20 5 ATLAS
HIGH EXPLOIT AVAIL

picklescan: arbitrary file read bypasses RCE blocklist

CVE-2026-53872
7.5
EPSS 0.5%
Data Extraction Supply Chain Framework Model
picklescan 3 5 ATLAS
HIGH EXPLOIT AVAIL

PickleScan: pty.spawn bypass enables RCE in model scans

CVE-2025-71322
8.8
EPSS 0.4%
Supply Chain Code Execution Model Framework
PickleScan CWE-693 3 5 ATLAS
HIGH

WPBot Pro: subscriber file deletion → system DoS

CVE-2025-60223
7.7
EPSS 0.4%
DoS Auth Bypass Plugin
wpbot-pro 3 ATLAS
HIGH

OpenClaw: allowlist bypass allows unauthorized shell exec

CVE-2026-53866
8.1
EPSS 0.3%
Auth Bypass Code Execution Agent Framework
openclaw CWE-184 4 5 ATLAS
HIGH

OpenClaw: path traversal enables arbitrary local code exec

CVE-2026-53865
7.1
EPSS 0.1%
Code Execution Supply Chain Agent Framework
openclaw CWE-426 4 3 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