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 1908 results — High severityCVE-2025-71359picklescan: scan bypass lets malicious models RCE8.10.6%picklescanJul 4HIGHECVE-2025-71356picklescan: torch.fx gadget bypasses malicious-pickle detection8.10.4%picklescanJul 4HIGHECVE-2025-71353picklescan: detection bypass allows pickle RCE8.10.4%picklescanJul 4HIGHECVE-2025-71347picklescan: numpy.f2py bypass lets malicious pickle evade scan8.10.6%picklescanJul 4HIGHECVE-2025-71345picklescan: scanner blocklist bypass hides pickle RCE8.10.5%picklescanJul 4HIGHECVE-2025-71343picklescan: scanner bypass lets malicious pickle files evade detection8.10.4%picklescanJul 4HIGHECVE-2025-71342picklescan: idlelib bypass hides pickle RCE8.10.5%picklescanJul 4HIGHCVE-2026-45499Azure OpenAI: SSRF flaw enables privilege escalation8.80.8%—Jul 2HIGHECVE-2026-50180langroid: SQL blocklist bypass leaks Postgres files—0.7%langroidJul 2HIGHECVE-2026-50181Langroid: path traversal escapes sandboxed file tools7.10.2%langroidJul 2HIGHGHSA-p73f-w79w-jqr5OpenClaw: owner-command auth bypass via native cmds——openclawJul 2HIGHGHSA-j472-gf56-x589OpenClaw: PowerShell alias bypasses exec allowlist——openclawJul 2HIGHGHSA-77q5-rr5v-x43qOpenClaw: retry hostname check leaks auth material——openclawJul 2HIGHGHSA-w5ww-7chg-mxcqOpenClaw: Telegram callback bypasses sender allowlist——openclawJul 2HIGHGHSA-xr4f-mjxj-w6w5OpenClaw: chat auth bypass enables device pairing hijack8.3—openclawJul 2HIGHGHSA-qjpc-qf9m-xwmrOpenClaw: WebSocket scope bypass grants admin authority8.8—openclawJul 2HIGHGHSA-c29c-2q9c-pc86OpenClaw: Slack allowFrom bypass via display-name spoof——openclawJul 2HIGHGHSA-jvm4-4j77-39p6OpenClaw: QQBot command bypasses config allowlist——openclawJul 2HIGHGHSA-83w9-h5wv-j9xmOpenClaw: TOCTOU race bypasses node approval scope——openclawJul 2HIGHGHSA-hw9r-h9mr-4jffOpenClaw: chat.send routing bypasses admin auth scopes8.8—openclawJul 2Frequently 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