Silmaril

Prompt injection defense that is self-healing

Y CombinatorSpring 2026ActiveB2BSecurity

What they do

Problem

AI applications and agents are vulnerable to prompt injection attacks that can cause security breaches and costly damages.

Solution

Silmaril provides a self-healing, context-aware prompt injection defense that plugs into agentic frameworks to detect and block threats with low latency.

Who it's for

Developers and enterprises building AI-native applications and agentic systems using frameworks like LangGraph.

Founders

Aum Upadhyay

Founder

Co-Founder & CEO at Silmaril. I built the security and privacy framework at AWS that prevented over $1.8B in damages. Now I bring that same defensive mindset to Silmaril, working with customers to ship prompt injection defense.

LinkedIn · X

Eduardo Velasco

Founder

Co-Founder & CTO at Silmaril. I prove the risks are real by finding exploits myself. I chained a prompt injection into root access inside ChatGPT. Ex-Amazon tech lead specializing in low latency ML models that generated $400M in annual revenue.

LinkedIn · X