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.
- CVSS severity
- EPSS exploit probability
- Exploitation confidence
- AI-component classification
- Compliance mappings
AI/ML CVEs Tracked
Critical
New This Week
In CISA KEV
Latest AI Security Threats
Showing 20 of 1332 results — High severity CVE-2026-41137 Flowise: RCE via CSVAgent unsanitized code injection 8.8 1.5% flowise Apr 23 HIGH GHSA-2r2p-4cgf-hv7h engramx: CSRF injects persistent prompts into AI agents — — — Apr 22 HIGH CVE-2026-6859 InstructLab: RCE via hardcoded trust_remote_code flag 8.8 0.4% instructlab Apr 22 HIGH CVE-2026-39861 Claude Code: sandbox escape via symlink allows arbitrary write — 0.7% @anthropic-ai/claude-code Apr 21 HIGH E CVE-2026-6596 Langflow: unauthenticated file upload allows RCE 7.3 0.3% langflow-base Apr 20 HIGH GHSA-mr34-9552-qr95 openclaw: path traversal leaks files and NTLM credentials — — 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 HIGH GHSA-66r7-m7xm-v49h openclaw: path traversal exposes host files via media tags — — openclaw Apr 17 HIGH GHSA-2cq5-mf3v-mx44 openclaw: exec approval bypass via opaque multi-call binaries — — openclaw Apr 17 HIGH GHSA-7jp6-r74r-995q openclaw: auth bypass lets write-scope callers mutate admin config — — openclaw Apr 17 HIGH GHSA-736r-jwj6-4w23 openclaw: sandbox escape via host=node exec routing bypass — — openclaw Apr 17 HIGH GHSA-939r-rj45-g2rj openclaw: untrusted plugin auto-enabled during onboarding — — openclaw Apr 17 HIGH GHSA-525j-hqq2-66r4 openclaw: CDP relay exposes browser DevTools on 0.0.0.0 — — openclaw Apr 17 HIGH GHSA-82qx-6vj7-p8m2 openclaw: trust bypass loads untrusted workspace plugins — — openclaw Apr 17 HIGH GHSA-vfp4-8x56-j7c5 openclaw: env denylist bypass enables code exec in agents — — openclaw Apr 17 HIGH GHSA-vw3h-q6xq-jjm5 openclaw: WebSocket DoS via oversized frame ingestion — — openclaw Apr 17 HIGH GHSA-8372-7vhw-cm6q openclaw: config redaction bypass exposes provider API keys — — openclaw Apr 17 HIGH GHSA-5fw2-mwhh-9947 Flowise: unauth TTS endpoint exposes stored AI API keys — — flowise 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