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 4331 resultsCVE-2026-5241transformers: trust_remote_code bypass enables RCE via model load9.60.6%transformersJun 3HIGHECVE-2026-4035MLflow: AI Gateway leaks cloud credentials via env injection7.70.5%mlflowJun 3HIGHCVE-2026-31942LibreChat: IDOR enables cross-user API key hijacking7.10.2%—Jun 2LOWCVE-2026-35202Pterodactyl: DB limit bypass via broken locking mechanism—0.2%—Jun 2HIGHCVE-2025-64390PS4 BD-J: sandbox escape via malformed JAR file7.40.1%—Jun 2CRITCVE-2026-47117OpenMed: RCE via trust_remote_code model loading9.80.9%openmedJun 2HIGHECVE-2026-5422jupyter-server: path traversal exposes sibling dir files8.14.9%jupyterJun 2MEDIECVE-2026-3198MLflow: auth bypass exposes gateway secrets and keys6.50.2%mlflowJun 2MEDIECVE-2026-10548hermes-agent: auth bypass exposes Anthropic API credentials5.30.1%—Jun 2MEDICVE-2026-28511eLabFTW: IDOR exposes restricted resource titles4.30.2%—Jun 1CRITCVE-2026-9319IBM WebSphere: RCE via JAX-WS deserialization (CVSS 9.0)9.00.5%—Jun 1MEDICVE-2026-43625CodexBar: session cookie leak via HTTP redirect5.90.2%—Jun 1HIGHECVE-2026-43624F5-TTS: path traversal enables arbitrary file write8.20.6%—Jun 1HIGHCVE-2026-38950AnomalyMatch: RCE via torch.load() unsafe deserialization7.80.1%—Jun 1HIGHECVE-2026-10118Poppler: PDF integer overflow enables heap RCE7.80.3%rhaiis/vllm-spyre-rhel9Jun 1HIGHECVE-2026-47412praisonai-platform: member can wipe entire workspace8.10.5%praisonai-platformJun 1HIGHECVE-2026-47415praisonai-platform: IDOR exposes cross-workspace tenant data8.30.4%praisonai-platformJun 1CRITECVE-2026-47413praisonai-platform: member can escalate to workspace owner9.60.3%praisonai-platformJun 1MEDIECVE-2026-47411PraisonAI: auth bypass allows workspace settings injection6.50.3%praisonai-platformJun 1HIGHECVE-2026-47417praisonai-platform: IDOR enables cross-tenant comment exfil8.10.4%praisonai-platformJun 1Frequently 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