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

96

New This Week

25

In CISA KEV

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

Latest AI Security Threats

Showing 20 of 169 results — Critical severity, has patch
CRITICALEXPLOIT AVAIL

openclaude: sandbox bypass allows host-level RCE

CVE-2026-42074
--
EPSS 0.6%
Prompt InjectionCode ExecutionAuth BypassAgentFrameworkPlugin
openclaudePatch: 0.5.1CWE-2846.3K6 ATLAS
CRITICALEXPLOIT AVAIL

PraisonAI: MCP path traversal escalates to full RCE

CVE-2026-44336
9.6
EPSS 0.6%
Prompt InjectionCode ExecutionData ExtractionAgentPluginFramework
PraisonAIPatch: 4.6.34CWE-2018 ATLAS
CRITICALSCANNER

open-webui: LDAP auth bypass — full account takeover

CVE-2026-44551
9.1
EPSS 1.5%
Auth BypassData ExtractionFrameworkAPI
open-webuiPatch: 0.9.0CWE-28724 ATLAS
CRITICALEXPLOIT AVAIL

vm2: sandbox escape via nesting:true enables RCE

CVE-2026-44007
9.1
EPSS 1.0%
Code ExecutionAuth BypassAgentFramework
vm2Patch: 3.11.1CWE-2841.9K5 ATLAS
CRITICALEXPLOIT AVAIL

Langflow: path traversal allows arbitrary directory deletion

CVE-2026-42048
9.6
EPSS 4.2%
DoSAuth BypassFrameworkRAG
langflowPatch: 1.9.0CWE-223 ATLAS
CRITICAL

Gemini CLI: RCE via malicious workspace in CI/CD

GHSA-wpqr-6v78-jr5g
10.0
Code ExecutionPrompt InjectionSupply ChainAgentFramework
@google/gemini-cliPatch: 0.39.1CWE-207 ATLAS
CRITICAL

litellm: SQLi exposes all managed LLM API credentials

GHSA-r75f-5x8p-qvmc
--
Auth BypassData ExtractionInferenceAPI
litellmPatch: 1.83.7CWE-8965 ATLAS
CRITICALEXPLOIT AVAIL

Flowise: prompt injection → unsandboxed RCE via CSV Agent

CVE-2026-41264
9.8
EPSS 1.8%
Prompt InjectionCode ExecutionAgentFramework
flowise-componentsPatch: 3.1.0CWE-1845 ATLAS
CRITICAL

Flowise: prompt injection bypasses Python sandbox RCE

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

OpenClaw: auth bypass enables unauthenticated command exec

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

PraisonAI: RCE via MCP command injection

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

Flowise CSVAgent: RCE via Python code injection

GHSA-9wc7-mj3f-74xv
--
Code ExecutionAuth BypassAgentFramework
flowise-componentsPatch: 3.1.0CWE-945 ATLAS
CRITICALEXPLOIT AVAIL

Flowise: RCE via MCP stdio command injection

CVE-2026-40933
9.9
EPSS 12.0%
Code ExecutionSupply ChainAuth BypassAgentPluginFramework
flowise-componentsPatch: 3.1.0CWE-787 ATLAS
CRITICAL

PraisonAI: auth bypass enables browser session hijack

GHSA-8x8f-54wf-vv92
9.1
Auth BypassData ExtractionCode ExecutionAgentPlugin
PraisonAIPatch: 4.5.139CWE-30615 ATLAS
CRITICAL

PraisonAI: RCE via malicious workflow YAML execution

GHSA-vc46-vw85-3wvm
9.8
Code ExecutionSupply ChainAgentFramework
PraisonAIPatch: 4.5.139CWE-7816 ATLAS
CRITICALEXPLOIT AVAIL

PraisonAI: path traversal allows arbitrary file write via recipe unpack

CVE-2026-40157
--
EPSS 0.4%
Supply ChainCode ExecutionAgentFramework
PraisonAIPatch: 4.5.128CWE-2213 ATLAS
CRITICALEXPLOIT AVAIL

PraisonAI: supply chain RCE via unverified template exec

CVE-2026-40154
9.3
EPSS 0.3%
Supply ChainCode ExecutionAgentPluginFramework
PraisonAIPatch: 4.5.128CWE-82917 ATLAS
CRITICALEXPLOIT AVAILSCANNER

lollms: Stored XSS enables wormable account takeover

CVE-2026-1115
9.6
EPSS 1.3%
Code ExecutionAuth BypassData ExtractionFrameworkAPI
lollmsPatch: 2.2.0CWE-795 ATLAS
CRITICALEXPLOIT AVAIL

PraisonAI: RCE via shell injection in memory hooks executor

CVE-2026-40111
--
EPSS 0.2%
Code ExecutionPrompt InjectionAgentFramework
praisonaiagentsPatch: 1.5.128CWE-78205 ATLAS
CRITICAL

PraisonAI: RCE via shell injection in agent workflows

GHSA-2763-cj5r-c79m
9.7
Code ExecutionPrompt InjectionSupply ChainAgentFramework
PraisonAIPatch: 4.5.121CWE-7816 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