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

openclaw-claude-bridge: sandbox bypass exposes CLI tools

CVE-2026-39398
--
Code Execution Auth Bypass Prompt Injection Agent Plugin
claude-code CWE-276 4 ATLAS
MEDIUM

Ollama: SSRF in Model Pull API enables network pivot

CVE-2026-5530
6.3
EPSS 0.3%
Data Extraction Privacy Violation Inference API
CWE-918 4 ATLAS
MEDIUM

Directus: cleartext storage exposes AI API keys

GHSA-mvv8-v4jj-g47j
6.5
Data Leakage Data Extraction Auth Bypass API Framework Agent
CWE-200 6 ATLAS
MEDIUM

OpenClaw before 2026.3.24 contains a sandbox bypass vulnerability in the message tool that allows attackers to read arbitrary local files by using mediaUrl and...

CVE-2026-33581
6.5
EPSS 0.6%
OpenClaw 4
MEDIUM

OpenClaw before 2026.3.28 contains a missing rate limiting vulnerability in the Nextcloud Talk webhook authentication that allows attackers to brute-force weak...

CVE-2026-33580
6.5
EPSS 0.4%
OpenClaw 4
MEDIUM

OpenClaw before 2026.3.28 contains a sender policy bypass vulnerability in the Google Chat and Zalouser extensions where route-level group allowlist policies...

CVE-2026-33578
4.3
EPSS 0.3%
OpenClaw 4
MEDIUM

OpenClaw before 2026.3.28 downloads and stores inbound media from Zalo channels before validating sender authorization. Unauthorized senders can force network...

CVE-2026-33576
6.5
EPSS 0.4%
OpenClaw 4
MEDIUM

OpenClaw before 2026.3.8 contains a sender allowlist bypass vulnerability in its Microsoft Teams plugin that allows unauthorized senders to bypass intended...

CVE-2026-34506
4.3
EPSS 0.3%
OpenClaw 4
MEDIUM

OpenClaw before 2026.3.12 applies rate limiting only after successful webhook authentication, allowing attackers to bypass rate limits and brute-force webhook...

CVE-2026-34505
6.5
EPSS 0.3%
OpenClaw 4
MEDIUM

OpenClaw before 2026.3.11 contains a sandbox boundary bypass vulnerability in the fs-bridge writeFile commit step that uses an unanchored container path during...

CVE-2026-32977
6.3
EPSS 0.1%
OpenClaw 4
MEDIUM

OpenClaw before 2026.3.11 contains an authorization bypass vulnerability allowing channel commands to mutate protected sibling-account configuration despite...

CVE-2026-32976
6.5
EPSS 0.2%
OpenClaw 4
MEDIUM

OpenClaw before 2026.3.8 contains an approval bypass vulnerability in system.run where mutable script operands are not bound across approval and execution...

CVE-2026-32921
6.3
EPSS 0.2%
OpenClaw 4
MEDIUM

OpenClaw before 2026.3.8 contains a path traversal vulnerability in the skills download installer that validates the tools root lexically but reuses the...

CVE-2026-33574
6.2
EPSS 0.1%
OpenClaw 4
MEDIUM

OpenClaw before 2026.3.11 contains an authorization bypass vulnerability in Discord guild reaction ingestion that fails to enforce member users and roles...

CVE-2026-32923
5.4
EPSS 0.2%
OpenClaw 4
MEDIUM

OpenClaw before 2026.3.11 contains an authorization bypass vulnerability allowing write-scoped callers to reach admin-only session reset logic. Attackers with...

CVE-2026-32919
6.1
EPSS 0.1%
OpenClaw 4
MEDIUM

DOMPurify: mXSS bypass achieves XSS via parse-context switch

GHSA-h8r8-wccr-v5f2
--
Code Execution Supply Chain Framework
CWE-79 5 ATLAS
MEDIUM EXPLOIT AVAIL

smolagents: code injection via incomplete sandbox fix

CVE-2026-4963
6.3
EPSS 0.6%
Code Execution Supply Chain Agent Framework
smolagents CWE-74 93 5 ATLAS
MEDIUM EXPLOIT AVAIL

Wallos: SSRF allows internal network access

CVE-2026-33401
6.5
EPSS 0.3%
Data Extraction Auth Bypass Privacy Violation Inference API
CWE-918 4 ATLAS
MEDIUM

OpenClaw versions prior to 2026.3.7 contain a sandbox escape vulnerability in the /acp spawn command that allows authorized sandboxed sessions to initialize...

CVE-2026-27646
6.1
EPSS 0.1%
OpenClaw 4
MEDIUM

OpenClaw versions prior to 2026.3.7 contain a shell approval gating bypass vulnerability in system.run dispatch-wrapper handling that allows attackers to skip...

CVE-2026-27183
5.3
EPSS 0.1%
OpenClaw 4

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