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 481 results — Critical severity CVE-2025-66455 LMDeploy is a toolkit for compressing, deploying,... 9.8 0.7% lmdeploy Sep 18 CRIT E CVE-2025-59953 LMdeploy has Remote Code Execution by Pickle... 9.8 0.7% lmdeploy Sep 16 CRIT E CVE-2026-57148 PraisonAI is a multi-agent teams system. Prior to... 9.8 0.4% — Sep 15 CRIT CVE-2026-57147 PraisonAI is a multi-agent teams system. Prior to... 9.8 0.8% — Sep 15 CRIT CVE-2026-57141 PraisonAI is a multi-agent teams system. Prior to... 9.8 0.5% — Sep 15 CRIT CVE-2026-57140 PraisonAI is a multi-agent teams system. From... 9.4 0.4% — Sep 15 CRIT E CVE-2026-57139 PraisonAI is a multi-agent teams system. From... 9.8 0.4% — Sep 15 CRIT E CVE-2026-57138 PraisonAI is a multi-agent teams system. From... 9.9 0.4% — Sep 15 CRIT CVE-2026-12944 IBM Langflow OSS 1.0.0 through 1.10.0 can allow... 9.6 0.2% — Sep 14 CRIT CVE-2026-57145 PraisonAI: path traversal lets agents read/write any file 9.1 0.4% praisonai Sep 14 CRIT E CVE-2026-57131 PraisonAI: no-auth API exposes agent execution 9.8 1.0% praisonai Sep 14 CRIT E CVE-2026-57127 PraisonAI: auth middleware fails open, exposes agents 9.8 0.9% praisonai Sep 14 CRIT E CVE-2026-57124 PraisonAI: unauth RCE via MCP connect endpoint 9.8 0.6% praisonai Sep 14 CRIT E CVE-2026-57125 PraisonAI: unauth RCE via YAML approval bypass 9.8 0.4% praisonai Sep 14 CRIT CVE-2026-57123 PraisonAI: unauthenticated MCP tool server enables RCE 9.8 0.5% praisonaiagents Sep 14 CRIT CVE-2026-87988 Mistral Vibe: unvalidated paths let agent escape workspace — 0.3% mistral-vibe Sep 11 CRIT E CVE-2026-87987 Mistral Vibe: env-var trick bypasses command allowlist — 0.3% mistral-vibe Sep 11 CRIT CVE-2026-87986 Mistral Vibe: shell parser bypass enables unapproved RCE — 0.4% mistral-vibe Sep 11 CRIT CVE-2026-87985 Mistral Vibe: ANSI-C quote bypass enables RCE — 0.4% mistral-vibe Sep 11 CRIT CVE-2026-87984 Mistral Vibe: shell redirection bypasses file-write guardrails — 0.4% mistral-vibe Sep 11 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