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
3,024

AI/ML CVEs Tracked

424

Critical

113

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 3024 results
MEDIUM

OpenClaw: env injection exposes MiniMax API key

GHSA-h2vw-ph2c-jvwf
--
Data Extraction Supply Chain Auth Bypass Agent API
openclaw Patch: 2026.4.20 CWE-15 4 4 ATLAS 1 incident
LOW

openclaw: SSRF policy bypass in CDP browser profile creation

GHSA-j4c5-89f5-f3pm
--
Auth Bypass Data Extraction Agent
openclaw Patch: 2026.4.20 CWE-918 4 4 ATLAS 1 incident
LOW

OpenClaw: auth bypass enables cross-device session hijack

GHSA-xrq9-jm7v-g9h7
--
Auth Bypass Agent
openclaw Patch: 2026.4.20 CWE-284 4 4 ATLAS 1 incident
LOW

openclaw: SSRF in QQBot media upload bypasses validation

GHSA-c4qg-j8jg-42q5
--
Supply Chain Data Extraction Agent Plugin
openclaw Patch: 2026.4.20 CWE-918 4 3 ATLAS 1 incident
MEDIUM

openclaw: env var injection via MCP stdio config

GHSA-mj59-h3q9-ghfh
--
Supply Chain Code Execution Agent Plugin
openclaw Patch: 2026.4.20 CWE-427 4 5 ATLAS 1 incident
LOW

openclaw: trust-label bypass amplifies prompt injection

GHSA-57r2-h2wj-g887
--
Prompt Injection Auth Bypass Agent Framework
openclaw Patch: 2026.4.20 CWE-345 4 4 ATLAS 1 incident
MEDIUM

openclaw: env namespace injection steers agent runtime

GHSA-hxvm-xjvf-93f3
--
Supply Chain Code Execution Agent Plugin
openclaw Patch: 2026.4.20 CWE-184 4 4 ATLAS 1 incident
MEDIUM

openclaw: DM policy bypass via Feishu card-action callbacks

GHSA-72q8-jcmc-97wx
--
Auth Bypass Agent Plugin
openclaw Patch: 2026.4.20 CWE-863 4 3 ATLAS 1 incident
LOW

OpenClaw: auth scope bypass exposes assistant-media files

GHSA-v8qf-fr4g-28p2
--
Auth Bypass Data Extraction Agent API
openclaw Patch: 2026.4.20 CWE-863 4 4 ATLAS 1 incident
MEDIUM

openclaw: session key auth bypass in webhook routing

GHSA-2xcp-x87w-q377
--
Auth Bypass Agent Framework
openclaw Patch: 2026.4.20 CWE-639 4 3 ATLAS 1 incident
MEDIUM

n8n-mcp: credential exposure via HTTP transport logging

GHSA-wg4g-395p-mqv3
4.3
Data Leakage Privacy Violation Agent Plugin
n8n-mcp Patch: 2.47.13 CWE-532 16 4 ATLAS
HIGH

litellm: RCE via MCP test endpoints privilege bypass

GHSA-v4p8-mg3p-g94g
--
Auth Bypass Code Execution API Inference
litellm Patch: 1.83.7 CWE-78 6 5 ATLAS
LOW

langchain-openai: SSRF via DNS rebinding in image token counter

CVE-2026-41488
3.1
EPSS 0.2%
Data Extraction Auth Bypass Framework Agent
langchain CWE-918 3.0K 3 ATLAS
MEDIUM

LangChain: SSRF redirect bypass exposes internal endpoints

CVE-2026-41481
6.5
EPSS 0.3%
Data Extraction Auth Bypass Framework RAG
langchain CWE-918 3.0K 3 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
HIGH

Claude Code: git worktree trust bypass executes hooks

CVE-2026-40068
--
EPSS 0.3%
Auth Bypass Code Execution Supply Chain Agent Framework Plugin
@anthropic-ai/claude-code Patch: 2.1.84 CWE-20 5 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
HIGH

Ray: Parquet RCE via Arrow extension deserialization

CVE-2026-41486
--
EPSS 0.5%
Code Execution Supply Chain Framework Training Data
ray Patch: 2.55.0 CWE-94 620 5 ATLAS
HIGH

LiteLLM: RCE via unsandboxed prompt template rendering

GHSA-xqmj-j6mv-4862
--
Code Execution Data Extraction Inference API
litellm Patch: 1.83.7 CWE-1336 6 5 ATLAS
MEDIUM

BetterDocs: Auth bypass drains OpenAI API quota

CVE-2026-6393
4.3
EPSS 0.3%
Auth Bypass DoS Data Extraction API Plugin
CWE-862 5 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