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
3,590

AI/ML CVEs Tracked

481

Critical

95

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 481 results — Critical severity
CRITICAL EXPLOIT AVAIL

PraisonAI: MCP path traversal escalates to full RCE

CVE-2026-44336
9.6
EPSS 0.6%
Prompt Injection Code Execution Data Extraction Agent Plugin Framework
PraisonAI Patch: 4.6.34 CWE-20 1 8 ATLAS
CRITICAL EXPLOIT AVAIL

cline: WebSocket auth bypass enables terminal RCE

CVE-2026-44211
9.6
EPSS 0.2%
Auth Bypass Code Execution Data Leakage Agent Plugin
cline CWE-306 2 7 ATLAS
CRITICAL SCANNER

open-webui: LDAP auth bypass — full account takeover

CVE-2026-44551
9.1
EPSS 1.5%
Auth Bypass Data Extraction Framework API
open-webui Patch: 0.9.0 CWE-287 3 4 ATLAS
CRITICAL KEV SCANNER

LiteLLM: SQL injection exposes LLM API credentials

CVE-2026-42208
9.8
EPSS 89.4%
Auth Bypass Data Extraction Supply Chain API Inference
litellm CWE-89 6 5 ATLAS
CRITICAL EXPLOIT AVAIL

vm2: sandbox escape via nesting:true enables RCE

CVE-2026-44007
9.1
EPSS 1.0%
Code Execution Auth Bypass Agent Framework
vm2 Patch: 3.11.1 CWE-284 1.8K 5 ATLAS
CRITICAL EXPLOIT AVAIL

Langflow: path traversal allows arbitrary directory deletion

CVE-2026-42048
9.6
EPSS 4.4%
DoS Auth Bypass Framework RAG
langflow Patch: 1.9.0 CWE-22 3 ATLAS
CRITICAL

Ollama: heap OOB read leaks API keys and chat data

CVE-2026-7482
9.1
EPSS 2.2%
Data Extraction Data Leakage Auth Bypass Inference Model
ollama 1.8K 5 ATLAS
CRITICAL

Ollama: path traversal + unsigned update = silent RCE

CVE-2026-42249
9.8
EPSS 0.6%
Code Execution Supply Chain Inference
ollama CWE-22 1.8K 4 ATLAS
CRITICAL

Ollama: silent auto-update bypasses signature check on Windows

CVE-2026-42248
9.8
EPSS 0.4%
Supply Chain Code Execution Inference
ollama CWE-494 1.8K 5 ATLAS
CRITICAL

Gemini CLI: RCE via malicious workspace in CI/CD

GHSA-wpqr-6v78-jr5g
10.0
Code Execution Prompt Injection Supply Chain Agent Framework
@google/gemini-cli Patch: 0.39.1 CWE-20 7 ATLAS
CRITICAL

litellm: SQLi exposes all managed LLM API credentials

GHSA-r75f-5x8p-qvmc
--
Auth Bypass Data Extraction Inference API
litellm Patch: 1.83.7 CWE-89 6 5 ATLAS
CRITICAL EXPLOIT AVAIL

Flowise: Cypher injection via GraphCypherQAChain node

CVE-2026-41274
9.8
EPSS 0.5%
Data Extraction Code Execution Agent Framework
flowise CWE-943 5 ATLAS
CRITICAL EXPLOIT AVAIL

KTransformers: pickle RCE via unauthenticated ZMQ socket

CVE-2026-26210
9.8
EPSS 0.7%
Code Execution Auth Bypass Inference Framework
ktransformers 9.5K 4 ATLAS
CRITICAL EXPLOIT AVAIL

Flowise: auth bypass enables full account takeover via reset

CVE-2026-41276
9.8
EPSS 6.9%
Auth Bypass Data Extraction Code Execution Agent Framework
flowise CWE-287 5 ATLAS
CRITICAL EXPLOIT AVAIL

Flowise: unauthenticated RCE via NODE_OPTIONS env injection

CVE-2026-41268
9.8
EPSS 13.8%
Code Execution Auth Bypass Agent Framework
flowise 6 ATLAS
CRITICAL EXPLOIT AVAIL

Flowise: mass assignment auth bypass in registration

CVE-2026-41267
9.8
EPSS 0.3%
Auth Bypass Data Extraction Privacy Violation Agent Framework
flowise CWE-639 5 ATLAS
CRITICAL EXPLOIT AVAIL

Flowise: RCE via prompt injection in Airtable Agent

CVE-2026-41265
9.8
EPSS 0.6%
Prompt Injection Code Execution Agent Framework
flowise 7 ATLAS
CRITICAL EXPLOIT AVAIL

Flowise: prompt injection → unsandboxed RCE via CSV Agent

CVE-2026-41264
9.8
EPSS 1.4%
Prompt Injection Code Execution Agent Framework
flowise-components Patch: 3.1.0 CWE-184 5 ATLAS
CRITICAL

Flowise: prompt injection bypasses Python sandbox RCE

GHSA-v38x-c887-992f
--
Prompt Injection Code Execution Agent Framework
flowise-components Patch: 3.1.0 CWE-184 8 ATLAS
CRITICAL

OpenClaw: auth bypass enables unauthenticated command exec

GHSA-xh72-v6v9-mwhc
--
Auth Bypass Code Execution Agent Plugin
openclaw Patch: 2026.4.15 CWE-287 3 4 ATLAS 1 incident

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