AI
Breaking Wire
Content
Ecosystem
Community
Pricing
AI Vulnerability Database
932 vulnerabilities tracked — CVEs, prompt injection, model exploits.
CRITICAL
Remote Code Execution in Hugging Face Hub via Malicious Pickled Model Weights
PyTorch < 2.1.0
Hugging Face Hub (via user-uploaded models)
Any system using `torch.load` on untrusted model files
16 Apr 2025
5 views
Unpatched
CRITICAL
Previous
Page 66 of 78
Next
Remote Code Execution in LangChain via Unsandboxed Python REPL Tool
LangChain < 0.3.0
16 Apr 2025
25 views
Patched
CRITICAL
Indirect Prompt Injection in LangChain ReAct Agent via Web Content
LangChain < 0.1.0
AutoGPT < 0.4.0
AI agent architectures using web browsing and code execution tools
15 Apr 2025
1 views
Patched
CRITICAL
Remote Code Execution in LangChain ReAct Agents via Unsandboxed BashProcess Tool
LangChain 0.1.x
LangChain 0.2.x
15 Apr 2025
7 views
Unpatched
CRITICAL
CVE-2023-29374
Remote Code Execution in LangChain via Unsafe `LLMMathChain` Evaluation
langchain <=0.0.178
15 Apr 2025
4 views
Patched
HIGH
Indirect Prompt Injection in LangChain ReAct Agents Leading to Arbitrary Tool Execution
LangChain < 0.2.0
15 Apr 2025
3 views
Patched
CRITICAL
Indirect Prompt Injection in LangChain ReAct Agent Leads to Remote Code Execution via Shell Tool
langchain<=0.1.18
langchain-community<=0.0.30
15 Apr 2025
3 views
Patched
CRITICAL
Indirect Prompt Injection in LangChain ReAct Agents Allows Arbitrary Code Execution
LangChain <0.1.0 (with default tool configurations)
15 Apr 2025
8 views
Unpatched
CRITICAL
Remote Code Execution in LangChain Agents via Unsanitized Tool Input from LLM
LangChain < 0.1.0
15 Apr 2025
3 views
Patched
HIGH
Data Exfiltration in RAG Systems via Indirect Prompt Injection in Markdown Image Rendering
Custom RAG applications
Enterprise AI assistants
LLM-powered customer support bots
15 Apr 2025
31 views
Unpatched
CRITICAL
Arbitrary Code Execution in LangChain ReAct Agents via Insecure Tool Use
LangChain <0.1.0 when using tools like ShellTool, PythonAstREPLTool without sandboxing
15 Apr 2025
3 views
Unpatched
CRITICAL
CVE-2023-29374
Arbitrary Code Execution in LangChain's LLMMathChain via Unsafe Eval
LangChain < 0.0.179
15 Apr 2025
6 views
Patched