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
4,307

AI/ML CVEs Tracked

533

Critical

95

New This Week

25

In CISA KEV

Sort:DateCVSSEPSSKEV firstMost exploited
Filter:AllCriticalHighMediumKEV onlyActive exploitationHas patchNo patch

Latest AI Security Threats

Showing 20 of 1908 results — High severity
HIGHEXPLOIT AVAIL

LLaMA-Factory: RCE via malicious model path

CVE-2026-58116
8.8
EPSS 0.9%
Code ExecutionSupply ChainFrameworkModelTraining Data
llama-factoryCWE-944 ATLAS
HIGH

GLib: malformed D-Bus XML integer overflow causes DoS

CVE-2026-58016
7.5
DoSFrameworkInference
rhoai/odh-llama-stack-k8s-operator-rhel9142 ATLAS
HIGHEXPLOIT AVAIL

GLib: off-by-one in key file parser enables DoS

CVE-2026-58014
7.3
EPSS 0.6%
DoSInferenceFramework
rhaiis/vllm-cuda-rhel9942 ATLAS
HIGHEXPLOIT AVAIL

libarchive: RAR5 double free enables remote DoS

CVE-2026-14164
7.5
EPSS 0.8%
DoSInferenceFramework
rhaii/vllm-gaudi-rhel9943 ATLAS
HIGHEXPLOIT AVAIL

Pinpoint APM: SSRF via alarm webhook registration

CVE-2026-57947
8.5
EPSS 0.3%
Data LeakageAuth BypassInferencePlugin
pinpoint2 ATLAS
HIGH

Claude Code: worktree bug enables sandbox-escape RCE

CVE-2026-55607
--
EPSS 0.7%
Code ExecutionPrompt InjectionSupply ChainAgent
@anthropic-ai/claude-codePatch: 2.1.163CWE-225 ATLAS
HIGHEXPLOIT AVAIL

MLflow: missing authz in label schema CRUD API

CVE-2026-13484
8.8
EPSS 0.5%
Auth BypassAPIFramework
CWE-8622 ATLAS
HIGHEXPLOIT AVAIL

ZAP: insecure deserialization RCE via ViewState add-on

CVE-2026-57527
8.8
EPSS 0.7%
Code ExecutionPlugin
CWE-502
HIGH

Ollama: unauthenticated heap memory disclosure

CVE-2026-5757
7.5
EPSS 0.7%
Data LeakagePrivacy ViolationInferenceModel
Ollama1.9K3 ATLAS
HIGHEXPLOIT AVAIL

picklescan: scanner bypass enables RCE via pickle supply chain

CVE-2025-71340
8.1
EPSS 0.4%
Supply ChainCode ExecutionModelFramework
picklescanCWE-50235 ATLAS
HIGHEXPLOIT AVAIL

Flowise: password change fails to revoke sessions

CVE-2025-71335
8.1
EPSS 0.4%
Auth BypassData LeakageAgentFramework
FlowiseCWE-6134 ATLAS
HIGHEXPLOIT AVAIL

Flowise: unverified password change enables account takeover

CVE-2025-71328
8.3
EPSS 0.5%
Auth BypassData ExtractionAgentFramework
FlowiseCWE-6203 ATLAS
HIGHEXPLOIT AVAILSCANNER

Flowise: path traversal leaks database unauthenticated

CVE-2025-71324
7.5
EPSS 1.6%
Data ExtractionAuth BypassAgentFramework
FlowiseCWE-735 ATLAS
HIGHEXPLOIT AVAIL

3X-UI: authenticated file write leads to RCE

CVE-2026-55477
7.2
EPSS 0.6%
Code ExecutionAPI
github.com/mhsanaei/3x-ui/v2CWE-20514
HIGH

n8n: SQL injection in DB nodes via identifier values

CVE-2026-56351
8.2
EPSS 0.4%
Data ExtractionCode ExecutionAgentFramework
n8nCWE-89165 ATLAS
HIGHEXPLOIT AVAILSCANNER

Flowise: auth bypass exposes OAuth secrets in cleartext

CVE-2026-56270
7.5
EPSS 2.0%
Auth BypassData ExtractionData LeakageAgentFramework
FlowiseCWE-3065 ATLAS
HIGHEXPLOIT AVAIL

picklescan: scanner bypass allows RCE via pickle load

CVE-2025-71361
8.1
EPSS 0.4%
Supply ChainCode ExecutionModelFramework
picklescanCWE-9534 ATLAS
HIGHEXPLOIT AVAIL

picklescan: scanner bypass enables arbitrary code execution

CVE-2025-71354
8.1
EPSS 0.4%
Supply ChainCode ExecutionFrameworkModel
picklescanCWE-50235 ATLAS
HIGH

Claude Desktop: VM integrity bypass enables RCE

CVE-2026-7574
8.7
EPSS 0.1%
Code ExecutionSupply ChainData ExtractionAgentAPI
Claude Desktop Cowork6.3K5 ATLAS
HIGHEXPLOIT AVAIL

@rtk-ai/rtk-rewrite: RCE via shell injection in exec tool

CVE-2026-55249
8.8
EPSS 0.6%
Code ExecutionPrompt InjectionSupply ChainAgentPlugin
openclaw35 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