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
4,331

AI/ML CVEs Tracked

535

Critical

108

New This Week

25

In CISA KEV

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

Latest AI Security Threats

Showing 20 of 366 results — Critical severity, no patch
CRITICALEXPLOIT AVAIL

PraisonAI: codeMode sandbox escape allows RCE

CVE-2026-57138
9.9
EPSS 0.7%
Code ExecutionData LeakageAgentFrameworkPlugin
praisonaiCWE-18415 ATLAS
CRITICAL

Langflow: SSRF-driven root RCE via component imports

CVE-2026-12944
9.6
EPSS 0.4%
Code ExecutionData ExtractionAuth BypassFrameworkAgentPlugin
langflowCWE-9185 ATLAS
CRITICAL

PraisonAI: path traversal lets agents read/write any file

CVE-2026-57145
9.1
EPSS 0.5%
Prompt InjectionData LeakageCode ExecutionAgentPlugin
praisonaiCWE-2214 ATLAS
CRITICALEXPLOIT AVAIL

PraisonAI: no-auth API exposes agent execution

CVE-2026-57131
9.8
EPSS 1.0%
Auth BypassCode ExecutionData LeakageFrameworkAgentAPI
praisonai16 ATLAS
CRITICALEXPLOIT AVAIL

PraisonAI: auth middleware fails open, exposes agents

CVE-2026-57127
9.8
EPSS 0.9%
Auth BypassCode ExecutionData LeakageAgentAPIPlugin
praisonai13 ATLAS
CRITICALEXPLOIT AVAIL

PraisonAI: unauth RCE via MCP connect endpoint

CVE-2026-57124
9.8
EPSS 1.0%
Auth BypassCode ExecutionAgentPlugin
praisonaiCWE-7814 ATLAS
CRITICALEXPLOIT AVAIL

PraisonAI: unauth RCE via YAML approval bypass

CVE-2026-57125
9.8
EPSS 0.6%
Auth BypassCode ExecutionAgentFramework
praisonaiCWE-30614 ATLAS
CRITICALEXPLOIT AVAIL

PraisonAI: unauthenticated MCP tool server enables RCE

CVE-2026-57123
9.8
EPSS 0.9%
Auth BypassCode ExecutionAgentFramework
praisonaiagentsCWE-306204 ATLAS
CRITICAL

Mistral Vibe: unvalidated paths let agent escape workspace

CVE-2026-87988
--
EPSS 0.4%
Auth BypassData LeakageAgent
mistral-vibe4733 ATLAS
CRITICALEXPLOIT AVAIL

Mistral Vibe: env-var trick bypasses command allowlist

CVE-2026-87987
--
EPSS 0.6%
Code ExecutionAuth BypassAgentFramework
mistral-vibe4735 ATLAS
CRITICAL

Mistral Vibe: shell parser bypass enables unapproved RCE

CVE-2026-87986
--
EPSS 0.6%
Code ExecutionAuth BypassAgent
mistral-vibe4734 ATLAS
CRITICAL

Mistral Vibe: ANSI-C quote bypass enables RCE

CVE-2026-87985
--
EPSS 0.6%
Auth BypassCode ExecutionAgent
mistral-vibe4734 ATLAS
CRITICAL

Mistral Vibe: shell redirection bypasses file-write guardrails

CVE-2026-87984
--
EPSS 0.5%
Code ExecutionSupply ChainAuth BypassAgent
mistral-vibe4734 ATLAS
CRITICAL

Mistral Vibe: quoted paths bypass file read guard

CVE-2026-87983
--
EPSS 0.6%
Auth BypassData LeakageAgent
mistral-vibe4733 ATLAS
CRITICAL

Langflow: unauthenticated RCE via code injection

CVE-2026-81204
9.8
EPSS 0.9%
Code ExecutionSupply ChainFrameworkAgent
langflowCWE-942 ATLAS
CRITICAL

Langflow: unauthenticated OS command injection (CVSS 9.8)

CVE-2026-79724
9.8
EPSS 0.7%
Code ExecutionFrameworkAgent
langflowCWE-783 ATLAS
CRITICAL

Langflow: unauth RCE via public MCP endpoints

CVE-2026-85025
9.8
EPSS 0.6%
Auth BypassCode ExecutionData LeakageFrameworkAgentPlugin
langflowCWE-8633 ATLAS
CRITICAL

Flowise: unauthenticated RCE via prediction API endpoint

CVE-2026-52098
9.8
EPSS 1.1%
Code ExecutionAuth BypassAgentFramework
flowise3 ATLAS
CRITICALEXPLOIT AVAIL

Gemini CLI: RCE via malicious .env GEMINI_CLI_HOME override

CVE-2026-13745
--
EPSS 0.7%
Code ExecutionSupply ChainAgentPlugin
run-gemini-cli GitHub Action4 ATLAS
CRITICAL

Codex Desktop: Git config filter triggers sandbox-escape RCE

CVE-2026-19593
9.8
EPSS 0.5%
Code ExecutionAuth BypassPrivacy ViolationAgent
Codex Desktop1.8K3 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