AI Threat Alert
Attack Type
Data Extraction
Data extraction attacks target AI/ML systems to exfiltrate training data, model weights, user conversations, or other sensitive information. These vulnerabilities are critical in multi-tenant AI deployments.
396
Total CVEs
20
Pages
Page 4 of 20
Current
| Severity | CVE | Headline | Package | CVSS |
|---|---|---|---|---|
| CRITICAL | CVE-2025-47277 | vLLM: RCE via exposed TCPStore in distributed inference | vllm | 9.8 |
| MEDIUM | CVE-2025-46153 | PyTorch: Dropout inconsistency enables membership inference | pytorch | 5.3 |
| CRITICAL | CVE-2023-34540 | LangChain: RCE via JiraAPIWrapper crafted input | langchain | 9.8 |
| CRITICAL | CVE-2023-34541 | LangChain: RCE via unsafe load_prompt deserialization | langchain | 9.8 |
| CRITICAL | CVE-2023-36258 | LangChain: unauthenticated RCE via code injection | langchain | 9.8 |
| CRITICAL | CVE-2023-36188 | LangChain: RCE via PALChain unsanitized Python exec | langchain | 9.8 |
| HIGH | CVE-2023-36189 | LangChain SQLDatabaseChain: SQL injection, DB exfil | langchain | 7.5 |
| CRITICAL | CVE-2023-38860 | LangChain: RCE via unsanitized prompt parameter | langchain | 9.8 |
| CRITICAL | CVE-2023-38896 | LangChain: RCE via unsandboxed LLM code execution | langchain | 9.8 |
| HIGH | CVE-2023-46229 | LangChain: SSRF in URL loader exposes internal network | langchain | 8.8 |
| HIGH | CVE-2023-32786 | LangChain: prompt injection triggers SSRF via URL fetch | langchain | 7.5 |
| CRITICAL | CVE-2024-2057 | LangChain TFIDFRetriever: SSRF/RCE via load_local | langchain | 9.8 |
| HIGH | CVE-2024-3571 | LangChain: path traversal allows arbitrary file R/W | langchain | 8.8 |
| HIGH | CVE-2024-3095 | LangChain: SSRF in Web Retriever exposes cloud metadata | langchain | 7.7 |
| HIGH | CVE-2024-38459 | LangChain: Python REPL code execution without opt-in | langchain-experimental | 7.8 |
| HIGH | CVE-2024-21513 | langchain-experimental: RCE via eval() in VectorSQL chain | langchain-experimental | 8.5 |
| CRITICAL | CVE-2024-7042 | LangChainJS: prompt injection enables full graph DB takeover | langchain | 9.8 |
| CRITICAL | CVE-2024-7774 | LangChain.js: path traversal, arbitrary file read/write | langchain.js | 9.1 |
| CRITICAL | CVE-2024-8309 | LangChain GraphCypher: prompt injection enables DB wipe | langchain | 9.8 |
| MEDIUM | CVE-2024-10940 | langchain-core: file read via prompt template inputs | langchain-core | 5.3 |