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 1527 results — Medium severity
MEDIUM

OpenClaw: sender allowlist bypass via Slack thread context

CVE-2026-41358
5.4
EPSS 0.1%
Auth BypassPrompt InjectionData LeakageAgentPlugin
openclawPatch: 2026.4.2CWE-34634 ATLAS1 incident
MEDIUM

Langflow: eval() code injection → remote code execution

CVE-2026-7700
6.3
EPSS 0.3%
Code ExecutionData ExtractionFrameworkAgent
langflowPatch: 1.10.3CWE-744 ATLAS
MEDIUM

Langflow: command injection in code parser enables RCE

CVE-2026-7687
6.3
EPSS 3.0%
Code ExecutionData ExtractionFrameworkAgent
langflowCWE-744 ATLAS
MEDIUM

COCO Annotator: path traversal exposes host files

CVE-2026-7680
4.3
EPSS 0.5%
Data LeakageTraining DataAPI
3 ATLAS
MEDIUMEXPLOIT AVAIL

SGLang: deserialization in tokenizer loader enables RCE

CVE-2026-7669
5.6
EPSS 0.4%
Supply ChainCode ExecutionFrameworkInference
sglangCWE-209.8K3 ATLAS
MEDIUM

Langflow: path traversal allows arbitrary file read

CVE-2026-3345
6.5
EPSS 0.4%
Data ExtractionData LeakageFrameworkAgent
langflowCWE-223 ATLAS
MEDIUM

Langflow: path traversal enables arbitrary file write

CVE-2026-4502
6.5
EPSS 0.3%
Code ExecutionSupply ChainFrameworkAgent
langflowCWE-224 ATLAS
MEDIUM

Langflow Desktop: stored XSS enables credential theft

CVE-2026-3346
6.4
EPSS 0.2%
Data ExtractionAuth BypassFramework
langflowCWE-894 ATLAS
MEDIUM

IBM Langflow: SSRF enables internal network enumeration

CVE-2026-3340
6.5
EPSS 0.2%
Data ExtractionPrivacy ViolationFrameworkAgent
langflowCWE-9184 ATLAS
MEDIUM

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

CVE-2026-6539
4.4
EPSS 0.2%
DoSData LeakageSupply ChainPlugin
MEDIUM

openclaw: path traversal exposes host files via audio embed

GHSA-gfg9-5357-hv4c
--
Prompt InjectionData ExtractionAgentPlugin
openclawPatch: 2026.4.15CWE-2235 ATLAS1 incident
MEDIUM

openclaw: auth bypass in owner command enforcement

GHSA-c28g-vh7m-fm7v
--
Auth BypassAgentPlugin
openclawPatch: 2026.4.21CWE-86235 ATLAS1 incident
MEDIUMEXPLOIT AVAIL

vllm: uninitialized KV cache memory leaks inference data

CVE-2026-7141
5.6
EPSS 0.3%
Data LeakageDoSInferenceFramework
vllmPatch: 0.19.1CWE-908944 ATLAS
MEDIUM

openclaw: config guard bypass, persistent settings mutation

GHSA-7jm2-g593-4qrc
--
Prompt InjectionAuth BypassAgentFrameworkPlugin
openclawPatch: 2026.4.20CWE-28534 ATLAS1 incident
MEDIUM

openclaw: tool policy bypass via bundled MCP/LSP tools

GHSA-qrp5-gfw2-gxv4
--
Auth BypassCode ExecutionAgentPlugin
openclawPatch: 2026.4.20CWE-86234 ATLAS1 incident
MEDIUM

OpenClaw: env injection exposes MiniMax API key

GHSA-h2vw-ph2c-jvwf
--
Data ExtractionSupply ChainAuth BypassAgentAPI
openclawPatch: 2026.4.20CWE-1534 ATLAS1 incident
MEDIUM

openclaw: env var injection via MCP stdio config

GHSA-mj59-h3q9-ghfh
--
Supply ChainCode ExecutionAgentPlugin
openclawPatch: 2026.4.20CWE-42735 ATLAS1 incident
MEDIUM

openclaw: env namespace injection steers agent runtime

GHSA-hxvm-xjvf-93f3
--
Supply ChainCode ExecutionAgentPlugin
openclawPatch: 2026.4.20CWE-18434 ATLAS1 incident
MEDIUM

openclaw: DM policy bypass via Feishu card-action callbacks

GHSA-72q8-jcmc-97wx
--
Auth BypassAgentPlugin
openclawPatch: 2026.4.20CWE-86333 ATLAS1 incident
MEDIUM

openclaw: session key auth bypass in webhook routing

GHSA-2xcp-x87w-q377
--
Auth BypassAgentFramework
openclawPatch: 2026.4.20CWE-63933 ATLAS1 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