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 337 results — Critical severity CVE-2026-31238 Ludwig: RCE via unsafe pickle deserialization in model serve 9.8 0.5% ludwig May 12 CRIT CVE-2026-31229 ART: torch.load() RCE via insecure deserialization 9.8 0.6% — May 12 CRIT E CVE-2026-42074 openclaude: sandbox bypass allows host-level RCE — 0.4% openclaude May 12 CRIT CVE-2026-31214 torch-checkpoint: unsafe pickle deserialization RCE 9.8 0.5% — May 12 CRIT E CVE-2026-43995 Flowise: SSRF in agent tools bypasses security wrapper 9.8 0.4% flowise May 11 CRIT E CVE-2026-44336 PraisonAI: MCP path traversal escalates to full RCE 9.6 0.5% PraisonAI May 11 CRIT E CVE-2026-44211 cline: WebSocket auth bypass enables terminal RCE 9.6 0.2% cline May 8 CRIT E CVE-2026-44551 open-webui: LDAP auth bypass — full account takeover 9.1 1.3% open-webui May 8 CRIT CVE-2026-42208 LiteLLM: SQL injection exposes LLM API credentials 9.8 93.1% litellm May 8 CRIT E CVE-2026-44007 vm2: sandbox escape via nesting:true enables RCE 9.1 0.8% vm2 May 7 CRIT E CVE-2026-42048 Langflow: path traversal allows arbitrary directory deletion 9.6 0.5% langflow May 5 CRIT CVE-2026-7482 Ollama: heap OOB read leaks API keys and chat data 9.1 0.8% ollama May 4 CRIT CVE-2026-42249 Ollama: path traversal + unsigned update = silent RCE 9.8 0.6% ollama Apr 29 CRIT CVE-2026-42248 Ollama: silent auto-update bypasses signature check on Windows 9.8 0.4% ollama Apr 29 CRIT GHSA-wpqr-6v78-jr5g Gemini CLI: RCE via malicious workspace in CI/CD 10.0 — @google/gemini-cli Apr 24 CRIT GHSA-r75f-5x8p-qvmc litellm: SQLi exposes all managed LLM API credentials — — litellm Apr 24 CRIT E CVE-2026-41274 Flowise: Cypher injection via GraphCypherQAChain node 9.8 0.5% flowise Apr 23 CRIT CVE-2026-26210 KTransformers: pickle RCE via unauthenticated ZMQ socket 9.8 — ktransformers Apr 23 CRIT E CVE-2026-41276 Flowise: auth bypass enables full account takeover via reset 9.8 6.9% flowise Apr 23 CRIT E CVE-2026-41268 Flowise: unauthenticated RCE via NODE_OPTIONS env injection 9.8 0.8% flowise Apr 23 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