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
3,589

AI/ML CVEs Tracked

481

Critical

94

New This Week

24

In CISA KEV

Sort: Date CVSS EPSS KEV first Most exploited
Filter: All Critical High Medium KEV only Active exploitation Has patch No patch

Latest AI Security Threats

Showing 20 of 481 results — Critical severity
CRITICAL

LMDeploy is a toolkit for compressing, deploying, and serving large language models. Starting in version 0.9.2 and prior to version 0.16.0, LMDeploy's PyTorch...

CVE-2025-66455
9.8
EPSS 0.7%
lmdeploy Patch: 0.16.0 CWE-502 1
CRITICAL EXPLOIT AVAIL

LMdeploy has Remote Code Execution by Pickle Deserialization via zmq_rpc.call_and_response() in InterLM/lmdeploy

CVE-2025-59953
9.8
EPSS 0.7%
lmdeploy Patch: 0.10.2 CWE-502 1
CRITICAL EXPLOIT AVAIL

PraisonAI is a multi-agent teams system. Prior to 0.1.6, praisonai_platform/services/auth_service.py falls back to the public dev-secret-change-me HS256...

CVE-2026-57148
9.8
EPSS 0.4%
CWE-287
CRITICAL

PraisonAI is a multi-agent teams system. Prior to 0.1.6, praisonai_platform/services/auth_service.py assigns the public dev-secret-change-me value to...

CVE-2026-57147
9.8
EPSS 0.8%
CWE-798
CRITICAL

PraisonAI is a multi-agent teams system. Prior to 1.7.2, the codeMode tool in src/praisonai-ts/src/tools/builtins/code-mode.ts executes model-generated...

CVE-2026-57141
9.8
EPSS 0.5%
CWE-94
CRITICAL

PraisonAI is a multi-agent teams system. From 1.6.0 until 1.7.2, AgentOS in src/praisonai-ts/src/os/agentos.ts uses the 0.0.0.0 default from...

CVE-2026-57140
9.4
EPSS 0.4%
CWE-306
CRITICAL EXPLOIT AVAIL

PraisonAI is a multi-agent teams system. From 1.5.0 until 1.7.2, MCPServer.startHttp() in src/praisonai-ts/src/mcp/server.ts binds without a host restriction...

CVE-2026-57139
9.8
EPSS 0.4%
CWE-306
CRITICAL EXPLOIT AVAIL

PraisonAI is a multi-agent teams system. From 1.4.0 until 1.7.2, codeMode in src/praisonai-ts/src/tools/builtins/code-mode.ts executes untrusted JavaScript...

CVE-2026-57138
9.9
EPSS 0.4%
CWE-184
CRITICAL

IBM Langflow OSS 1.0.0 through 1.10.0 can allow attackers to execute arbitrary Python code with root privileges (UID=0) on the Langflow server by submitting...

CVE-2026-12944
9.6
EPSS 0.2%
CWE-918
CRITICAL

PraisonAI: path traversal lets agents read/write any file

CVE-2026-57145
9.1
EPSS 0.4%
Prompt Injection Data Leakage Code Execution Agent Plugin
praisonai CWE-22 1 4 ATLAS
CRITICAL EXPLOIT AVAIL

PraisonAI: no-auth API exposes agent execution

CVE-2026-57131
9.8
EPSS 1.0%
Auth Bypass Code Execution Data Leakage Framework Agent API
praisonai 1 6 ATLAS
CRITICAL EXPLOIT AVAIL

PraisonAI: auth middleware fails open, exposes agents

CVE-2026-57127
9.8
EPSS 0.9%
Auth Bypass Code Execution Data Leakage Agent API Plugin
praisonai 1 3 ATLAS
CRITICAL EXPLOIT AVAIL

PraisonAI: unauth RCE via MCP connect endpoint

CVE-2026-57124
9.8
EPSS 0.6%
Auth Bypass Code Execution Agent Plugin
praisonai CWE-78 1 4 ATLAS
CRITICAL EXPLOIT AVAIL

PraisonAI: unauth RCE via YAML approval bypass

CVE-2026-57125
9.8
EPSS 0.4%
Auth Bypass Code Execution Agent Framework
praisonai CWE-306 1 4 ATLAS
CRITICAL

PraisonAI: unauthenticated MCP tool server enables RCE

CVE-2026-57123
9.8
EPSS 0.5%
Auth Bypass Code Execution Agent Framework
praisonaiagents CWE-306 20 4 ATLAS
CRITICAL

Mistral Vibe: unvalidated paths let agent escape workspace

CVE-2026-87988
--
EPSS 0.3%
Auth Bypass Data Leakage Agent
mistral-vibe 492 3 ATLAS
CRITICAL EXPLOIT AVAIL

Mistral Vibe: env-var trick bypasses command allowlist

CVE-2026-87987
--
EPSS 0.3%
Code Execution Auth Bypass Agent Framework
mistral-vibe 492 5 ATLAS
CRITICAL

Mistral Vibe: shell parser bypass enables unapproved RCE

CVE-2026-87986
--
EPSS 0.4%
Code Execution Auth Bypass Agent
mistral-vibe 492 4 ATLAS
CRITICAL

Mistral Vibe: ANSI-C quote bypass enables RCE

CVE-2026-87985
--
EPSS 0.4%
Auth Bypass Code Execution Agent
mistral-vibe 492 4 ATLAS
CRITICAL

Mistral Vibe: shell redirection bypasses file-write guardrails

CVE-2026-87984
--
EPSS 0.4%
Code Execution Supply Chain Auth Bypass Agent
mistral-vibe 492 4 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