Executive Summary
Guardion's AI Incidents Database aggregates AI security incidents, including prompt injection and sandbox breakout flaws in Cursor workflows and the scanner-to-LiteLLM supply chain compromise.
What Happened
The database aggregates recent AI security incidents and disclosures, including prompt-injection and sandbox-breakout flaws in Cursor-related workflows and malicious package activity tied to LiteLLM. It also notes a supply-chain incident in which attackers compromised a scanner tool and used it to steal publishing tokens before pushing malicious releases of a widely used LLM gateway library.
Affected Products
- Cursor
- LiteLLM
Vulnerability / Attack Technique
Multiple AI incidents (database)
Technical Mechanism
Aggregated incident records.
AI Security Category
LLM03:2025 Supply Chain
Part of the AI Supply Chain and AI SBOM topic.
Relevant Frameworks
RealGround Analysis
Useful reference for tracking AI incidents.
Recommended Controls
- Track AI incidents relevant to your stack
Related RealGround Service
AI Agent SBOM and LLM Mapping · or start with the free AI Agent Security Scanner.
Sources
Guardion AI: https://guardion.ai/ai-incidents
Summary and analysis written by RealGround from the source above; last updated 2026-10-18.