Disclosures
The attack techniques, behaviors, and vulnerabilities uncovered through these disclosures feed Mindgard’s proprietary knowledge base and continuously strengthen our AI Security Platform.
156
Vulnerabilities reported
Submitted to affected vendors
132
Vulnerabilities accepted
Confirmed valid by vendors
98
Vulnerabilities patched
Vendor fix confirmed
24
Affected vendors
Distinct organizations
38
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
Anyscale Ray Serve IP Spoofing via CRLF Injected Trust Headers
Anyscale
Upcoming
Anyscale Ray Serve Header Injection via CRLF
Anyscale
Upcoming
NVIDIA Triton Inference Server WAF Bypass via Content-Type Header Ignored
NVIDIA
Upcoming
NVIDIA Triton Inference Server DoS via Zero-Dimension Shape
NVIDIA
Upcoming
NVIDIA Triton Inference Server DoS via Arbitrary POSIX SHM Access and Unregister-All
NVIDIA
Upcoming
NVIDIA Triton Inference Server Log Forgery via Log File Content Injection
NVIDIA
Upcoming
NVIDIA Triton Inference Server DoS via Gzip Decompression Amplification
NVIDIA
Upcoming
NVIDIA Triton Inference Server Cross-Site Scripting via Request ID Reflection
NVIDIA
Upcoming
NVIDIA Triton Inference HTTP Request Smuggling via CL-TE
NVIDIA
Upcoming
NVIDIA Triton Inference Server HTTP Request Smuggling via TE Obfuscation Variants
NVIDIA
Upcoming
NVIDIA Triton Inference Server Code Execution via Trace File Content Injection
NVIDIA
Upcoming
Gemini CLI Code Execution via TOCTOU Trust Persistence
Google
Upcoming
Anthropic Claude Code Code Execution via TOCTOU Config Poisoning Trust Persistence
Anthropic
Upcoming
Anthropic Claude Code Configuration Poisoning Remote Code Execution
Anthropic
Upcoming
OpenAI Codex Code Execution via TOCTOU Trust Persistence
OpenAI
Upcoming
Title
Vendor
Status
Published
TheLibrarian.io Internal Cloud Environment Access via web_fetch Tool
TheLibrarian.io
Published
December 17, 2025
Cline Bot AI Coding Agent Code Execution via Prompt Injection and TOCTOU Script Invocation
Cline
Published
November 18, 2025
Cline Bot AI Coding Agent Code Execution via Prompt Injection and .clinerules Directives
Cline
Published
November 18, 2025
Cline Bot AI Coding Agent Data Exfiltration via Prompt Injection and DNS
Cline
Published
November 18, 2025
