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
4,330

AI/ML CVEs Tracked

535

Critical

107

New This Week

25

In CISA KEV

Sort:DateCVSSEPSSKEV firstMost exploited
Filter:AllCriticalHighMediumKEV onlyActive exploitationHas patchNo patch

Latest AI Security Threats

Showing 20 of 4330 results
MEDIUM

nbconvert: path traversal exfiltrates files via HTML export

CVE-2026-39378
6.5
EPSS 0.3%
Data ExtractionSupply ChainFrameworkPlugin
nbconvertPatch: 7.17.1CWE-223.0K4 ATLAS
MEDIUM

nbconvert: path traversal enables arbitrary file write

CVE-2026-39377
6.5
EPSS 0.3%
Supply ChainCode ExecutionFramework
nbconvertPatch: 7.17.1CWE-223.0K3 ATLAS
HIGH

Claude Code: sandbox escape via symlink allows arbitrary write

CVE-2026-39861
--
EPSS 0.7%
Code ExecutionPrompt InjectionAuth BypassAgent
@anthropic-ai/claude-codePatch: 2.1.64CWE-225 ATLAS
MEDIUMEXPLOIT AVAIL

FastChat: control flow flaw corrupts arena comparison

CVE-2026-6608
5.3
EPSS 0.3%
Adversarial ExamplesSupply ChainFrameworkAPI
fschatCWE-6707353 ATLAS
LOWEXPLOIT AVAIL

Langflow: stored XSS in chat message editor

CVE-2026-6600
3.5
EPSS 0.2%
Code ExecutionData ExtractionFrameworkAgent
langflowCWE-794 ATLAS
MEDIUMEXPLOIT AVAIL

Langflow: MCP config injection via X-Forwarded-For header

CVE-2026-6599
6.3
EPSS 0.2%
Auth BypassCode ExecutionSupply ChainFrameworkAgentPlugin
langflowCWE-744 ATLAS
MEDIUMEXPLOIT AVAIL

Langflow: cleartext auth storage exposes API keys

CVE-2026-6598
4.3
EPSS 0.2%
Data ExtractionPrivacy ViolationFramework
langflowPatch: 1.9.1CWE-3125 ATLAS
LOWEXPLOIT AVAIL

langflow: Plaintext credential storage via Flow API

CVE-2026-6597
2.7
EPSS 0.4%
Data LeakageData ExtractionFrameworkAPI
langflowCWE-2555 ATLAS
HIGHEXPLOIT AVAIL

Langflow: unauthenticated file upload allows RCE

CVE-2026-6596
7.3
EPSS 0.3%
Code ExecutionAuth BypassFrameworkAgent
langflow-basePatch: 0.9.1CWE-2844 ATLAS
CRITICAL

Flowise: prompt injection bypasses Python sandbox RCE

GHSA-v38x-c887-992f
--
Prompt InjectionCode ExecutionAgentFramework
flowise-componentsPatch: 3.1.0CWE-1848 ATLAS
MEDIUM

OpenClaw: path traversal in memory_get reads arbitrary workspace files

GHSA-f934-5rqf-xx47
--
Data ExtractionAuth BypassAgentPlugin
openclawPatch: 2026.4.15CWE-2234 ATLAS1 incident
HIGH

openclaw: path traversal leaks files and NTLM credentials

GHSA-mr34-9552-qr95
--
Data ExtractionData LeakageAgentPlugin
openclawPatch: 2026.4.15CWE-2234 ATLAS1 incident
CRITICAL

OpenClaw: auth bypass enables unauthenticated command exec

GHSA-xh72-v6v9-mwhc
--
Auth BypassCode ExecutionAgentPlugin
openclawPatch: 2026.4.15CWE-28734 ATLAS1 incident
HIGH

OpenClaw: auth bypass lets DM senders run room commands

GHSA-2gvc-4f3c-2855
--
Auth BypassCode ExecutionAgent
openclawPatch: 2026.4.15CWE-86333 ATLAS1 incident
HIGH

OpenClaw: stale bearer token survives SecretRef rotation

GHSA-xmxx-7p24-h892
--
Auth BypassAgentAPI
openclawPatch: 2026.4.15CWE-32433 ATLAS1 incident
HIGH

PraisonAI: SQL injection across 9 DB backends

GHSA-rg3h-x3jw-7jm5
8.1
Data ExtractionCode ExecutionData LeakageFrameworkAgent
praisonaiagentsPatch: 1.6.8CWE-89204 ATLAS
CRITICAL

PraisonAI: RCE via MCP command injection

GHSA-9qhq-v63v-fv3j
9.8
Code ExecutionSupply ChainAgentFramework
praisonaiPatch: 4.5.149CWE-7816 ATLAS
MEDIUM

Claude Code: config hijack via unprotected ProgramData dir

CVE-2026-35603
--
EPSS 0.1%
Supply ChainAuth BypassAgent
@anthropic-ai/claude-codePatch: 2.1.75CWE-4264 ATLAS
MEDIUM

openclaw: CDP SSRF enables internal host pivot

GHSA-f7fh-qg34-x2xh
--
Auth BypassData ExtractionAgentFramework
openclawPatch: 2026.4.5CWE-91832 ATLAS1 incident
MEDIUM

OpenClaw: auth bypass leaks host files via media path

GHSA-jhpv-5j76-m56h
--
Auth BypassData ExtractionAgentPlugin
openclawPatch: 2026.4.10CWE-86334 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