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 1583 results — no patch CVE-2026-31249 CosyVoice: insecure deserialization RCE via .pt files — 0.2% — May 11 MEDI E CVE-2026-44708 mistune: math plugin XSS bypasses escape=True control 6.1 0.2% mistune May 8 CRIT E CVE-2026-44211 cline: WebSocket auth bypass enables terminal RCE 9.6 0.2% cline May 8 MEDI CVE-2026-42282 n8n-MCP: credential logging exposes OAuth tokens in HTTP mode 4.3 0.3% — May 8 HIGH CVE-2026-42271 LiteLLM: RCE via MCP test endpoint command injection 8.8 75.0% litellm May 8 CRIT CVE-2026-42208 LiteLLM: SQL injection exposes LLM API credentials 9.8 84.1% litellm May 8 HIGH CVE-2026-42203 LiteLLM: SSTI in prompt template endpoint enables RCE 8.8 0.3% litellm May 8 LOW E CVE-2026-8026 Flowise: info disclosure via login API response handler 3.7 0.3% flowise May 6 MEDI E CVE-2026-43901 wireshark-mcp: path traversal enables arbitrary file write via MCP 6.8 0.3% — May 5 MEDI E CVE-2026-42045 LobeChat: XSS-to-RCE via exposed Electron IPC 6.2 0.3% @lobehub/lobehub May 5 LOW E CVE-2026-7847 Langchain-Chatchat: predictable file IDs leak uploaded files 2.6 0.2% langchain-chatchat May 5 LOW E CVE-2026-7846 Langchain-Chatchat: TOCTOU race allows silent file overwrite 2.6 0.2% langchain-chatchat May 5 LOW E CVE-2026-7845 Langchain-Chatchat: weak image hash allows integrity bypass 2.6 0.1% langchain-chatchat May 5 MEDI E CVE-2026-7844 Langchain-Chatchat: auth bypass on file service endpoints 6.3 0.3% — May 5 CRIT CVE-2026-7482 Ollama: heap OOB read leaks API keys and chat data 9.1 1.0% ollama May 4 MEDI CVE-2026-7700 Langflow: eval() code injection → remote code execution 6.3 0.3% langflow May 3 MEDI CVE-2026-7687 Langflow: command injection in code parser enables RCE 6.3 1.7% langflow May 3 MEDI E CVE-2026-7669 SGLang: deserialization in tokenizer loader enables RCE 5.6 0.4% sglang May 2 HIGH CVE-2026-6543 Langflow: RCE exposes API keys and DB credentials 8.8 0.5% langflow Apr 30 HIGH CVE-2026-6542 Langflow: IDOR exposes cross-tenant flow data and deletion 8.1 0.2% langflow Apr 30 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