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: local file exfiltration via trusted MEDIA refs

GHSA-qqq7-4hxc-x63c
--
Data ExtractionPrivacy ViolationAgentPlugin
openclawPatch: 2026.4.8CWE-66834 ATLAS1 incident
MEDIUM

OpenClaw: eval approval bypass enables unintended code exec

GHSA-q2gc-xjqw-qp89
--
Auth BypassCode ExecutionAgentFramework
openclawPatch: 2026.4.8CWE-2035 ATLAS1 incident
MEDIUMEXPLOIT AVAIL

libcap: TOCTOU race in cap_set_file() enables privesc

CVE-2026-4878
6.7
EPSS 0.2%
Code ExecutionAuth BypassInference
rhaiis/vllm-spyre-rhel9942 ATLAS
MEDIUM

LangChain: f-string template injection exposes object internals

GHSA-926x-3r5x-gfhw
5.3
Data ExtractionPrompt InjectionFramework
langchain-corePatch: 0.3.84CWE-206.3K4 ATLAS
MEDIUM

OpenClaw: request body replay leaks credentials via redirect

CVE-2026-40037
6.5
EPSS 0.3%
Data ExtractionData LeakageAgent
OpenClaw35 ATLAS1 incident
MEDIUMEXPLOIT AVAIL

openai-realtime-ui: SSRF in API proxy endpoint

CVE-2026-5803
6.3
EPSS 0.2%
Data ExtractionAuth BypassAPI
CWE-9183 ATLAS
MEDIUM

praisonaiagents: agent context leak + path traversal

GHSA-766v-q9x3-g744
6.5
Data LeakageData ExtractionAgentFramework
praisonaiagentsPatch: 1.5.115CWE-22204 ATLAS
MEDIUMEXPLOIT AVAIL

LobeChat: auth bypass via forged XOR obfuscated header

CVE-2026-39411
5.0
EPSS 0.1%
Auth BypassData ExtractionDoSAPIInference
@lobehub/lobehubPatch: 2.1.48CWE-2871.8K5 ATLAS
MEDIUMEXPLOIT AVAIL

lollms: sessions persist after password reset

CVE-2026-1163
4.1
EPSS 0.2%
Auth BypassData ExtractionAPIAgent
lollmsCWE-6133 ATLAS
MEDIUM

openclaw-claude-bridge: sandbox bypass exposes CLI tools

CVE-2026-39398
--
Code ExecutionAuth BypassPrompt InjectionAgentPlugin
claude-codeCWE-2764 ATLAS
MEDIUM

OpenClaw: cleartext WebSocket exposes gateway credentials

GHSA-83f3-hh45-vfw9
--
Data LeakageAuth BypassAgent
openclawPatch: 2026.4.2CWE-20033 ATLAS1 incident
MEDIUM

openclaw: timing side-channel leaks shared-secret length

GHSA-jj6q-rrrf-h66h
--
Auth BypassData ExtractionAgentFramework
openclawPatch: 2026.4.2CWE-20833 ATLAS1 incident
MEDIUM

OpenClaw: Zalo webhook dedup collision silently drops events

GHSA-rxmx-g7hr-8mx4
--
DoSAgentAPI
openclawPatch: 2026.4.2CWE-34932 ATLAS
MEDIUM

OpenClaw: CDP host bypass exposes localhost browser state

GHSA-fh32-73r9-rgh5
--
Auth BypassData ExtractionAgentPlugin
openclawPatch: 2026.4.2CWE-2034 ATLAS1 incident
MEDIUM

openclaw: script swap bypasses pnpm dlx approval

GHSA-w6wx-jq6j-6mcj
--
Auth BypassCode ExecutionSupply ChainAgentPlugin
openclawPatch: 2026.4.2CWE-86334 ATLAS1 incident
MEDIUM

OpenClaw: approval bypass via env key normalization gap

GHSA-98ch-45wp-ch47
--
Auth BypassCode ExecutionAgentFramework
openclawPatch: 2026.4.2CWE-17834 ATLAS1 incident
MEDIUM

OpenClaw: info disclosure exposes host filesystem paths

GHSA-2f7j-rp58-mr42
--
Data LeakagePrivacy ViolationAgentFramework
openclawPatch: 2026.4.2CWE-20033 ATLAS
MEDIUM

OpenClaw: untrusted plugin RCE via workspace channel setup

GHSA-2qrv-rc5x-2g2h
--
Supply ChainCode ExecutionAuth BypassAgentPlugin
openclawPatch: 2026.4.2CWE-82934 ATLAS1 incident
MEDIUM

OpenClaw: read-only scope bypass kills agent sessions

GHSA-5hff-46vh-rxmw
--
Auth BypassDoSAgent
openclawPatch: 2026.4.2CWE-26933 ATLAS
MEDIUM

openclaw: iOS bridge bypass enables unauthorized agent runs

GHSA-4p4f-fc8q-84m3
--
Auth BypassDoSAgent
openclawPatch: 2026.4.2CWE-28434 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