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
2,388

AI/ML CVEs Tracked

342

Critical

358

New This Week

18

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 844 results — Medium severity
MEDIUM

PraisonAI: SQL injection via table_prefix exposes DB

GHSA-x783-xp3g-mqhp
--
Data Extraction Auth Bypass Agent Framework
PraisonAI Patch: 4.5.133 CWE-89 1 4 ATLAS
MEDIUM

PraisonAI: tool approval bypass leaks env credentials

GHSA-ffp3-3562-8cv3
5.5
Auth Bypass Data Extraction Prompt Injection Agent Framework
praisonaiagents Patch: 4.5.128 CWE-863 11 5 ATLAS
MEDIUM EXPLOIT AVAIL

PraisonAI: MCP env inheritance exposes API keys

CVE-2026-40159
5.5
EPSS 0.2%
Supply Chain Data Leakage Data Extraction Agent Framework Plugin
PraisonAI Patch: 4.5.128 CWE-200 1 6 ATLAS
MEDIUM EXPLOIT AVAIL

PraisonAI: decompression bomb causes disk exhaustion

CVE-2026-40148
6.5
EPSS 0.2%
DoS Supply Chain Agent Framework
PraisonAI Patch: 4.5.128 CWE-409 1 4 ATLAS
MEDIUM EXPLOIT AVAIL

praisonaiagents: glob traversal leaks filesystem metadata

CVE-2026-40152
5.3
EPSS 0.3%
Data Extraction Privacy Violation Agent Plugin
praisonaiagents Patch: 1.5.128 CWE-22 11 5 ATLAS
MEDIUM EXPLOIT AVAIL SCANNER

PraisonAI: unauthenticated agent config and system prompt disclosure

CVE-2026-40151
5.3
EPSS 0.8%
Data Extraction Auth Bypass Agent API
PraisonAI Patch: 4.5.128 CWE-200 1 6 ATLAS
MEDIUM EXPLOIT AVAIL

PraisonAI: unbounded body read enables local DoS

CVE-2026-40115
6.2
EPSS 0.3%
DoS Auth Bypass Agent Framework
PraisonAI Patch: 4.5.128 CWE-770 1 3 ATLAS
MEDIUM

OpenClaw: ANSI injection spoof AI agent approval prompts

CVE-2026-35651
4.3
EPSS 0.3%
Social Engineering Supply Chain Auth Bypass Agent Plugin
openclaw CWE-150 4 5 ATLAS
MEDIUM

OpenClaw: webhook rebinding exposes user data

CVE-2026-35670
5.9
EPSS 0.2%
Auth Bypass Data Extraction Privacy Violation Agent API
OpenClaw 4 4 ATLAS 1 incident
MEDIUM

OpenClaw: SIGKILL bypass skips security-sensitive cleanup

CVE-2026-35667
6.1
EPSS 0.1%
DoS Data Leakage Agent
OpenClaw 4 3 ATLAS 1 incident
MEDIUM

OpenClaw: pre-auth resource exhaustion via Feishu webhook DoS

CVE-2026-35665
5.3
EPSS 0.3%
DoS Agent
OpenClaw 4 3 ATLAS
MEDIUM

OpenClaw: auth bypass enables unauthorized callback injection

CVE-2026-35664
5.3
EPSS 0.3%
Auth Bypass Agent
OpenClaw 4 3 ATLAS 1 incident
MEDIUM

OpenClaw: missing auth enables agent scope bypass

CVE-2026-35662
4.3
EPSS 0.2%
Auth Bypass Agent Framework
OpenClaw 4 3 ATLAS 1 incident
MEDIUM

OpenClaw: auth bypass mutates AI agent session state

CVE-2026-35661
5.3
EPSS 0.3%
Auth Bypass Agent
OpenClaw 4 3 ATLAS 1 incident
MEDIUM

OpenClaw: DNS-SD metadata hijacks CLI routing

CVE-2026-35659
4.6
EPSS 0.1%
Auth Bypass Data Extraction Agent Framework
OpenClaw 4 3 ATLAS 1 incident
MEDIUM

OpenClaw: sandbox bypass exposes host filesystem reads

CVE-2026-35658
6.5
EPSS 0.3%
Data Extraction Auth Bypass Agent Plugin
OpenClaw 4 4 ATLAS 1 incident
MEDIUM

OpenClaw: auth bypass via X-Forwarded-For spoofing

CVE-2026-35656
6.5
EPSS 0.3%
Auth Bypass Agent
OpenClaw 4 3 ATLAS 1 incident
MEDIUM

OpenClaw: identity spoofing bypasses agent safety checks

CVE-2026-35655
5.7
EPSS 0.2%
Auth Bypass Code Execution Agent Plugin
OpenClaw 4 4 ATLAS 1 incident
MEDIUM

OpenClaw: auth bypass on Teams feedback invoke

CVE-2026-35654
5.3
EPSS 0.2%
Auth Bypass Agent Plugin
OpenClaw 4 3 ATLAS 1 incident
MEDIUM

OpenClaw: auth bypass enables unauthorized action execution

CVE-2026-35652
6.5
EPSS 0.4%
Auth Bypass Code Execution Agent
OpenClaw 4 4 ATLAS 1 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