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 1961 results — Active exploitationCVE-2025-54413skops: RCE via MethodNode unsafe deserialization—0.2%skopsJul 26HIGHECVE-2025-54412skops: OperatorFuncNode type confusion → RCE—0.2%skopsJul 26MEDIECVE-2025-51471Ollama: auth token hijack via crafted WWW-Authenticate6.918.5%ollamaJul 22MEDIECVE-2025-51481Dagster: path traversal exposes arbitrary file read via gRPC6.60.6%—Jul 22MEDIECVE-2025-3933Transformers: ReDoS in DonutProcessor causes DoS5.30.5%transformersJul 11MEDIECVE-2025-6716Contest Gallery WP Plugin: Stored XSS in OpenAI integration6.40.2%—Jul 11MEDIECVE-2025-7021OpenAI Operator: fullscreen spoofing captures credentials6.50.4%operatorJul 10MEDIECVE-2025-6211llama-index: DocugamiReader MD5 hash collision drops chunks6.50.4%llama-index-readers-docugamiJul 10HIGHECVE-2025-6209llama_index: path traversal allows arbitrary file read7.50.6%llama-index-coreJul 7MEDIECVE-2025-5472llama-index: JSONReader DoS via recursive JSON parsing6.50.4%llama-index-coreJul 7MEDIECVE-2025-6210llama-index Obsidian reader: hardlink path traversal leaks files6.20.3%llama-index-readers-obsidianJul 7MEDIECVE-2025-3044llama-index ArxivReader: MD5 collision corrupts training data5.30.3%llama-index-readers-papersJul 7HIGHECVE-2025-3046LlamaIndex Obsidian: symlink traversal exposes host files7.50.6%llama-index-readers-obsidianJul 7HIGHECVE-2025-3225llama-index Papers Loader: XML expansion DoS7.50.5%llama-index-readers-papersJul 7LOWECVE-2025-3777Transformers: URL validation bypass exposes image pipeline3.50.4%transformersJul 7MEDIECVE-2025-3264Transformers: ReDoS in dynamic module loader causes DoS5.30.5%transformersJul 7MEDIECVE-2025-3263Transformers: ReDoS in config loader causes serving DoS5.30.5%transformersJul 7HIGHECVE-2025-3262Transformers: ReDoS in chat.py causes CPU exhaustion7.50.5%transformersJul 7MEDIECVE-2025-3108llama-index: RCE via unsafe pickle deserialization5.00.5%llama-index-coreJul 7MEDIECVE-2025-45809LiteLLM: SQL injection in key management API5.40.3%litellmJul 3Frequently 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