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-2026-55428Coder: agent IP spoofing hijacks workspace traffic8.20.4%github.com/coder/coder/v2Jul 6HIGHCVE-2026-55429Coder: cross-workspace agent hijack via app ID reuse8.70.5%github.com/coder/coder/v2Jul 6HIGHCVE-2026-55427Coder: SSH config injection via config-ssh enables RCE8.30.5%github.com/coder/coder/v2Jul 6HIGHCVE-2026-55077Coder: user-admin can hijack owner accounts7.20.6%github.com/coder/coder/v2Jul 6HIGHCVE-2026-55075Coder: OIDC auth bypass enables account takeover7.40.5%github.com/coder/coder/v2Jul 6HIGHCVE-2026-55076Coder: OIDC type-confusion enables account takeover7.40.6%github.com/coder/coder/v2Jul 6HIGHECVE-2026-54771Langroid: auth bypass invokes disabled tools via raw JSON8.10.4%langroidJul 6HIGHCVE-2026-49042Camel: input validation flaw in LLM agent tool components7.30.7%org.apache.camel:camel-spring-ai-toolsJul 6HIGHECVE-2026-14534fickling: denylist gaps let malicious pickles execute8.80.6%ficklingJul 4HIGHECVE-2026-12196HestiaCP: cronjob flaw lets low-priv users get root—0.4%—Jul 4HIGHCVE-2025-71380n8n: authenticated RCE via Execute Command node8.80.6%n8nJul 4HIGHECVE-2025-71375picklescan: detection bypass enables pickle RCE8.10.5%picklescanJul 4HIGHECVE-2025-71373picklescan: methodcaller bypass enables pickle RCE8.10.6%picklescanJul 4HIGHECVE-2025-71372Picklescan: RCE gadget bypasses pickle safety scanner8.10.5%picklescanJul 4HIGHECVE-2025-71369picklescan misses malicious pickles via torch decoder8.10.6%picklescanJul 4HIGHECVE-2025-71367picklescan: attrgetter bypass evades malicious pickle scan8.10.6%picklescanJul 4HIGHECVE-2025-71366picklescan: scan bypass lets malicious pickle RCE8.10.6%picklescanJul 4HIGHECVE-2025-71364picklescan: scanner blind spot enables pickle RCE8.10.7%picklescanJul 4HIGHECVE-2025-71362picklescan: scanner bypass enables RCE via numpy eval8.10.4%picklescanJul 4HIGHECVE-2025-71360picklescan: scanner bypass enables pickle RCE8.10.4%picklescanJul 4Frequently 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