AI Threat AlertAI 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 4330 resultsCVE-2026-42861Flowise: mass assignment breaks multi-tenant isolation—0.3%flowiseMay 14HIGHECVE-2026-45136claude-code-cache-fix: hook path injection → RCE—0.2%claude-code-cache-fixMay 13HIGHCVE-2026-45134LangSmith: prompt deserialization enables SSRF + data leak7.10.2%langchainMay 13HIGHECVE-2026-44246nnU-Net: prompt injection hijacks CI/CD triage agent7.20.3%claude-codeMay 12CRITCVE-2026-31233guardrails-ai: RCE via malicious Hub package manifest9.80.6%guardrails-aiMay 12CRITCVE-2026-31239mamba: RCE via unsafe torch.load() on model load9.80.4%mamba-ssmMay 12CRITCVE-2026-31238Ludwig: RCE via unsafe pickle deserialization in model serve9.80.5%ludwigMay 12HIGHCVE-2026-31232CosyVoice: RCE via unsafe torch.load() model deserialization8.80.5%—May 12CRITCVE-2026-31229ART: torch.load() RCE via insecure deserialization9.80.6%—May 12CRITECVE-2026-42074openclaude: sandbox bypass allows host-level RCE—0.6%openclaudeMay 12HIGHCVE-2026-31224snorkel: RCE via unsafe model deserialization8.80.4%snorkelMay 12HIGHCVE-2026-31222snorkel: RCE via insecure model checkpoint loading8.80.4%snorkelMay 12HIGHCVE-2026-31221pytorch-lightning: RCE via insecure checkpoint deserialization7.80.4%pytorch-lightningMay 12UNKNCVE-2026-31219optimate: RCE via unsafe torch.load() deserialization—0.6%—May 12UNKNCVE-2026-31218optimate: unsafe torch.load() enables RCE via model file—0.6%—May 12CRITCVE-2026-31214torch-checkpoint: unsafe pickle deserialization RCE9.80.5%—May 12HIGHECVE-2026-2614MLflow: path traversal allows unauthenticated file read7.53.7%mlflowMay 11MEDIECVE-2026-43979local-deep-research: HTML injection enables SSRF via WeasyPrint5.00.3%local-deep-researchMay 11CRITECVE-2026-43995Flowise: SSRF in agent tools bypasses security wrapper9.80.4%flowiseMay 11HIGHECVE-2026-2393MLflow: SSRF in webhook URL enables cloud credential theft7.10.3%mlflowMay 11Frequently 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