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

2,404

AI/ML CVEs Tracked

347

Critical

310

New This Week

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 827 results — has patch

Severity CVE ID Summary CVSS EPSS Package Date

HIGH CVE-2026-40068 Claude Code: git worktree trust bypass executes hooks — 0.3% @anthropic-ai/claude-code Apr 24 CRIT GHSA-r75f-5x8p-qvmc litellm: SQLi exposes all managed LLM API credentials — — litellm Apr 24 HIGH CVE-2026-41486 Ray: Parquet RCE via Arrow extension deserialization — 0.5% ray Apr 24 HIGH GHSA-xqmj-j6mv-4862 LiteLLM: RCE via unsandboxed prompt template rendering — — litellm Apr 24 MEDI CVE-2026-41495 n8n-mcp: bearer tokens exposed in HTTP transport logs 5.3 0.3% n8n-mcp Apr 23 CRIT E CVE-2026-41264 Flowise: prompt injection → unsandboxed RCE via CSV Agent 9.8 0.5% flowise-components Apr 21 MEDI CVE-2026-39378 nbconvert: path traversal exfiltrates files via HTML export 6.5 0.3% nbconvert Apr 21 MEDI CVE-2026-39377 nbconvert: path traversal enables arbitrary file write 6.5 0.3% nbconvert Apr 21 HIGH CVE-2026-39861 Claude Code: sandbox escape via symlink allows arbitrary write — 0.5% @anthropic-ai/claude-code Apr 21 MEDI E CVE-2026-6598 Langflow: cleartext auth storage exposes API keys 4.3 0.2% langflow Apr 20 HIGH E CVE-2026-6596 Langflow: unauthenticated file upload allows RCE 7.3 0.3% langflow-base Apr 20 CRIT GHSA-v38x-c887-992f Flowise: prompt injection bypasses Python sandbox RCE — — flowise-components Apr 18 MEDI GHSA-f934-5rqf-xx47 OpenClaw: path traversal in memory_get reads arbitrary workspace files — — openclaw Apr 17 HIGH GHSA-mr34-9552-qr95 openclaw: path traversal leaks files and NTLM credentials — — openclaw Apr 17 CRIT GHSA-xh72-v6v9-mwhc OpenClaw: auth bypass enables unauthenticated command exec — — openclaw Apr 17 HIGH GHSA-2gvc-4f3c-2855 OpenClaw: auth bypass lets DM senders run room commands — — openclaw Apr 17 HIGH GHSA-xmxx-7p24-h892 OpenClaw: stale bearer token survives SecretRef rotation — — openclaw Apr 17 HIGH GHSA-rg3h-x3jw-7jm5 PraisonAI: SQL injection across 9 DB backends 8.1 — praisonaiagents Apr 17 CRIT GHSA-9qhq-v63v-fv3j PraisonAI: RCE via MCP command injection 9.8 — praisonai Apr 17 MEDI CVE-2026-35603 Claude Code: config hijack via unprotected ProgramData dir — 0.1% @anthropic-ai/claude-code Apr 17

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