Finding and Disclosing Vulnerabilities Across the AI Ecosystem

Mindgard has uncovered and responsibly disclosed security weaknesses in AI models, developer tools, infrastructure, and applications.

Join others Red Teaming their AI

Research That Makes AI Security Stronger

The attack techniques, behaviors, and vulnerabilities uncovered through these disclosures feed Mindgard’s proprietary knowledge base and continuously strengthen our AI Security Platform.

183
Vulnerabilities reported
Submitted to affected vendors
139
Vulnerabilities accepted
Confirmed valid by vendors
98
Vulnerabilities patched
Vendor fix confirmed
31
Affected vendors
Distinct organizations
58
Affected products
Distinct AI systems & tools

Disclosures reported over time

Cumulative count by report date · mid-2025 to today
Cumulative

Affected vendors

Block area = number of disclosure records
156 records

All Disclosures

Published findings and vulnerabilities currently under coordinated disclosure.

Title
Vendor
Status
Published
NVIDIA TensorRT-LLM NIXL RDMA Write to Attacker-Controlled GPU Addresses via Notification MemoryDesc
NVIDIA
Upcoming
NVIDIA TensorRT-LLM Unauthenticated Disagg Cluster Storage Enables Fake Worker Registration -> Request Hijacking
NVIDIA
Upcoming
NVIDIA TensorRT-LLM Missing HMAC Key in trtllm-serve Disaggregated Launch Path
NVIDIA
Upcoming
NVIDIA TensorRT Arbitrary Code Execution via Embedded Plugin dlopen
NVIDIA
Upcoming
NVIDIA TensorRT Unbounded nbDims in Tensor Shape Deserialization Stack Buffer Overflow
NVIDIA
Upcoming
NVIDIA TensorRT Unchecked Shader Index in readEngineFromArchive Heap OOB Read
NVIDIA
Upcoming
Joblib Model File Scanner Bypass via Compressed Files
Joblib
Upcoming
Joblib Model File Path Traversal via NDArrayWrapper / ZNDArrayWrapper in Compat Format
Joblib
Upcoming
Joblib Model File Pickle Restriction Bypass via Hidden Payload in Array Data
Joblib
Upcoming
Microsoft ONNX Runtime Code Execution via Tile Operator Heap Buffer Overflow
Microsoft
Upcoming
Anyscale Ray Serve Internal HTTP Header Forging
Anyscale
Upcoming
Anyscale Ray Serve Cross-Site Scripting via X-Request-Id Response Header Reflection
Anyscale
Upcoming
Anyscale Ray Serve Code Execution via Replica gRPC Pickle Deserialization
Anyscale
Upcoming
Anyscale Ray Serve IP Spoofing via CRLF Injected Trust Headers
Anyscale
Upcoming
Anyscale Ray Serve Header Injection via CRLF
Anyscale
Upcoming