← back

MemPoison: Uncovering Persistent Memory Threats and Structural Blind Spots in LL

Persistent external memory enhances agent continuity but introduces persistent security vulnerabilities: adversarial content can be injected via standard interaction channels, retained across turns, and later distort downstream behavior. To

https://arxiv.org/abs/2607.14651v1 ↗
Thesis fit
Good fit

Within your typical scope; diligence still required.

Edit thesis
In your usual scope
Idea match None

How close the company’s idea is to your thesis statement

Sector ai

Overlap with sectors you care about

Geography Outside

Outside your target regions — scores 0

Your thesis: “We back exceptional technical founders building AI-first products and infrastructure, deploying $100K checks within 24 hours.”

Founder → stable Traction → stable Idea vs market ↓ declining
Generate memo
Add / edit details

Correct facts used on the next screening or memo.

Similar baseline plays (YC · idea space)

Mem0 · Active
The Memory layer for AI Agents
founders not scraped yet
Veria Labs · Active
Continuous AI pentesting that finds and fixes vulnerabilities
founders not scraped yet
Silmaril · Active
Runtime security for AI that self-improves
founders not scraped yet
Hex Security · Active
Agentic Offensive Security at Scale
founders not scraped yet
Fabraix · Active
The world's frontier hacker for AI agents.
founders not scraped yet