Vulnerability Disclosures

Responsible AI vulnerability disclosures for a safer & more resilient ecosystem

Upcoming Disclosures

Affected Vendor(s)

Affected Product(s)

Reported On

Mistral

Vibe CLI

Amazon

Kiro IDE

Amazon

Kiro IDE

TheLibrarian.io

TheLibrarian.io

JetBrains

Junie AI, IntelliJ IDEA, PyCharm, GoLand, CLion, Rider

Eclipse

Theia IDE

Zed Industries

Zed IDE

Zed Industries

Zed IDE

Published Disclosures

Title

Affected Vendor(s)

Published On

Google Antigravity IDE Persistent Code Execution

December 8, 2025

Cline Bot AI Coding Agent Code Execution via Prompt Injection and TOCTOU Script Invocation

December 9, 2025

Cline Bot AI Coding Agent Code Execution via Prompt Injection and .clinerules Directives

December 9, 2025

Cline Bot AI Coding Agent Data Exfiltration via Prompt Injection and DNS

December 9, 2025

Learn how Mindgard can help you navigate AI Security

Take the first step towards securing your AI. Book a demo now and we'll reach out to you.

Mindgard, the leading provider of Artificial Intelligence security solutions, helps enterprises secure their AI models, agents, and systems across the entire lifecycle. Mindgard’s solution uncovers shadow AI, conducts automated AI red teaming by emulating adversaries, and delivers runtime protection against attacks like prompt injection and agentic manipulation. Trusted by leading organizations in finance, healthcare, and technology, Mindgard is backed by investors including .406 Ventures, IQ Capital, Atlantic Bridge, and Lakestar.