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
3,023

AI/ML CVEs Tracked

424

Critical

115

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 3023 results
MEDIUM

OpenClaw: sender allowlist bypass via Slack thread context

CVE-2026-41358
5.4
EPSS 0.1%
Auth Bypass Prompt Injection Data Leakage Agent Plugin
openclaw Patch: 2026.4.2 CWE-346 4 4 ATLAS 1 incident
CRITICAL

Ollama: heap OOB read leaks API keys and chat data

CVE-2026-7482
9.1
EPSS 1.9%
Data Extraction Data Leakage Auth Bypass Inference Model
ollama 1.7K 5 ATLAS
HIGH

GnuTLS: DTLS fragment heap overflow, DoS on AI inference

CVE-2026-33846
7.5
EPSS 1.3%
DoS Code Execution Inference
rhaiis/vllm-rocm-rhel9 130 2 ATLAS
MEDIUM

Langflow: eval() code injection → remote code execution

CVE-2026-7700
6.3
EPSS 0.3%
Code Execution Data Extraction Framework Agent
langflow CWE-74 4 ATLAS
MEDIUM

Langflow: command injection in code parser enables RCE

CVE-2026-7687
6.3
EPSS 1.7%
Code Execution Data Extraction Framework Agent
langflow CWE-74 4 ATLAS
MEDIUM EXPLOIT AVAIL

SGLang: deserialization in tokenizer loader enables RCE

CVE-2026-7669
5.6
EPSS 0.4%
Supply Chain Code Execution Framework Inference
sglang CWE-20 9.2K 3 ATLAS
HIGH

Langflow: RCE exposes API keys and DB credentials

CVE-2026-6543
8.8
EPSS 0.5%
Code Execution Data Extraction Supply Chain Framework Agent
langflow CWE-94 5 ATLAS
HIGH

Langflow: IDOR exposes cross-tenant flow data and deletion

CVE-2026-6542
8.1
EPSS 0.2%
Data Extraction Privacy Violation Auth Bypass Framework Agent
langflow CWE-639 5 ATLAS
MEDIUM

Langflow: path traversal allows arbitrary file read

CVE-2026-3345
6.5
EPSS 0.4%
Data Extraction Data Leakage Framework Agent
langflow CWE-22 3 ATLAS
HIGH

Langflow Desktop: IDOR leaks user images unauthenticated

CVE-2026-4503
7.5
EPSS 0.3%
Privacy Violation Data Extraction Auth Bypass Framework Agent
langflow CWE-639 3 ATLAS
MEDIUM

Langflow: path traversal enables arbitrary file write

CVE-2026-4502
6.5
EPSS 0.3%
Code Execution Supply Chain Framework Agent
langflow CWE-22 4 ATLAS
MEDIUM

Langflow Desktop: stored XSS enables credential theft

CVE-2026-3346
6.4
EPSS 0.2%
Data Extraction Auth Bypass Framework
langflow CWE-89 4 ATLAS
MEDIUM

IBM Langflow: SSRF enables internal network enumeration

CVE-2026-3340
6.5
EPSS 0.2%
Data Extraction Privacy Violation Framework Agent
langflow CWE-918 4 ATLAS
MEDIUM

Notepad++: format string bug enables DoS, info leak

CVE-2026-6539
4.4
EPSS 0.2%
DoS Data Leakage Supply Chain Plugin
HIGH

n8n-mcp: SSRF bypass via IPv6 leaks API keys

CVE-2026-42449
8.5
EPSS 0.2%
Data Extraction Auth Bypass Supply Chain Agent Plugin
n8n-mcp Patch: 2.47.14 CWE-918 16 5 ATLAS
HIGH

GnuTLS: DTLS integer underflow enables OOB read/DoS

CVE-2026-33845
7.5
EPSS 0.8%
DoS Data Leakage Inference API
rhaiis/vllm-rocm-rhel9 130 2 ATLAS
HIGH

Jupyter Notebook: stored XSS enables full account takeover

CVE-2026-40171
--
EPSS 0.5%
Auth Bypass Code Execution Data Extraction Framework Training Data
@jupyterlab/help-extension Patch: 4.5.7 CWE-79 1.9K 7 ATLAS
UNKNOWN

@anthropic-ai/sdk: insecure file perms expose agent memory

CVE-2026-41686
--
EPSS 0.1%
Data Leakage Privacy Violation Prompt Injection Agent API Framework
@anthropic-ai/sdk Patch: 0.91.1 CWE-732 351 5 ATLAS
HIGH EXPLOIT AVAIL

marked: infinite recursion DoS crashes Node.js via OOM

CVE-2026-41680
7.5
EPSS 0.3%
DoS Framework
marked Patch: 18.0.2 CWE-400 6.3K 4 ATLAS
MEDIUM

openclaw: path traversal exposes host files via audio embed

GHSA-gfg9-5357-hv4c
--
Prompt Injection Data Extraction Agent Plugin
openclaw Patch: 2026.4.15 CWE-22 4 5 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