Posts about Security
Articles about Security from the GuardionAI team — AI agent security, runtime governance, and AI safety.
- Beyond Regex: Detecting Prompt Injection at the Gateway Layer Using ML Classification
Move beyond regex and LLM-as-judge for prompt injection detection. Learn how ML classifiers provide sub-millisecond, accurate prompt injection defense at the gateway.
- How Jira Tickets, Pull Requests, and Docs Become AI Exploit Vectors
Discover how AI agents reading Jira tickets, GitHub PRs, and internal docs can be exploited via indirect prompt injection, and how to secure developer workflows.
- Model Context Protocol (MCP): Understanding Security Risks and Controls
A deep dive into the security risks of the Model Context Protocol (MCP), including confused deputy attacks, SSRF, and token passthrough, along with best practices for mitigation.
Start securing your AI
Your agents are already running. Are they governed?
One Security Gateway. Total control. Live in under 30 minutes — zero instrumentation.
Deploy in < 30 minutes · Cancel anytime