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
2,377

AI/ML CVEs Tracked

337

Critical

392

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 534 results — Medium severity, no patch
MEDIUM EXPLOIT AVAIL

PraisonAI: XSS via no-op HTML sanitizer in agent output

CVE-2026-40112
5.4
EPSS 0.2%
Prompt Injection Code Execution Data Extraction Agent Framework RAG
praisonai CWE-79 1 4 ATLAS
MEDIUM

OpenClaw before 2026.3.22 contains an information disclosure vulnerability that allows attackers with operator.read scope to expose credentials embedded in...

CVE-2026-35644
6.5
OpenClaw 4
MEDIUM

OpenClaw before 2026.3.25 contains an authorization bypass vulnerability where group reaction events bypass the requireMention access control mechanism....

CVE-2026-35642
4.3
OpenClaw 4
MEDIUM

OpenClaw versions 2026.3.11 through 2026.3.24 contain a session isolation bypass vulnerability where session_status resolves sessionId to canonical session...

CVE-2026-35636
6.5
OpenClaw 4
MEDIUM

OpenClaw before 2026.3.22 contains a webhook path route replacement vulnerability in the Synology Chat extension that allows attackers to collapse...

CVE-2026-35635
4.8
OpenClaw 4
MEDIUM

OpenClaw before 2026.3.23 contains an authentication bypass vulnerability in the Canvas gateway where authorizeCanvasRequest() unconditionally allows...

CVE-2026-35634
5.1
OpenClaw 4
MEDIUM

OpenClaw before 2026.3.22 contains an unbounded memory allocation vulnerability in remote media HTTP error handling that allows attackers to trigger excessive...

CVE-2026-35633
5.3
OpenClaw 4
MEDIUM

OpenClaw before 2026.3.22 fails to enforce operator.admin scope on mutating internal ACP chat commands, allowing unauthorized modifications. Attackers without...

CVE-2026-35631
6.5
OpenClaw 4
MEDIUM

OpenClaw before 2026.3.25 contains a missing rate limiting vulnerability in Telegram webhook authentication that allows attackers to brute-force weak webhook...

CVE-2026-35628
4.8
OpenClaw 4
MEDIUM

OpenClaw before 2026.3.22 performs cryptographic and dispatch operations on inbound Nostr direct messages before enforcing sender and pairing policy...

CVE-2026-35627
6.5
OpenClaw 4
MEDIUM

OpenClaw before 2026.3.22 contains an unauthenticated resource exhaustion vulnerability in voice call webhook handling that buffers request bodies before...

CVE-2026-35626
5.3
OpenClaw 4
MEDIUM

OpenClaw before 2026.3.22 contains a policy confusion vulnerability in room authorization that matches colliding room names instead of stable room tokens....

CVE-2026-35624
4.2
OpenClaw 4
MEDIUM

OpenClaw before 2026.3.25 contains a missing rate limiting vulnerability in webhook authentication that allows attackers to brute-force weak webhook passwords...

CVE-2026-35623
4.8
OpenClaw 4
MEDIUM

OpenClaw before 2026.3.22 contains an improper authentication verification vulnerability in Google Chat app-url webhook handling that accepts add-on principals...

CVE-2026-35622
5.9
OpenClaw 4
MEDIUM

OpenClaw before 2026.3.23 contains a replay identity vulnerability in Plivo V2 signature verification that allows attackers to bypass replay protection by...

CVE-2026-35618
6.5
OpenClaw 4
MEDIUM

OpenClaw before 2026.3.25 contains an authorization bypass vulnerability in Google Chat group policy enforcement that relies on mutable space display names....

CVE-2026-35617
4.2
OpenClaw 4
MEDIUM

LangChain: template injection leaks object attributes

CVE-2026-40087
5.3
EPSS 0.3%
Prompt Injection Data Extraction Framework
langchain-core CWE-1336 4.8K 3 ATLAS
MEDIUM

OpenClaw before 2026.3.31 (patched in 2026.4.8) contains a request body replay vulnerability in fetchWithSsrFGuard that allows unsafe request bodies to be...

CVE-2026-40037
6.5
OpenClaw 4
MEDIUM EXPLOIT AVAIL

openai-realtime-ui: SSRF in API proxy endpoint

CVE-2026-5803
6.3
EPSS 0.2%
Data Extraction Auth Bypass API
CWE-918 3 ATLAS
MEDIUM EXPLOIT AVAIL

lollms: sessions persist after password reset

CVE-2026-1163
4.1
EPSS 0.2%
Auth Bypass Data Extraction API Agent
lollms CWE-613 3 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