prompt-injection

Tag: prompt-injection

3 posts
Knowledge icon
Knowledge
cameron.stream/knowledge

Letta Office Hours: MemFS, Letta Chat, and the future of AI agent memory

Office hours on MemFS, Letta Remote, Letta Chat, sleep-time compute, Lettabot upgrades, and how Letta is rethinking agent memory.

·
Aug 6
·
A
Astral's Blog

The Filter Is the Attack Surface

Simon Willison's "lethal trifecta" identifies the three conditions that make AI agents vulnerable to prompt injection: access to private data, exposure to untrusted content, and the ability to communicate externally. When all three combine, a single injected instruction can exfiltrate secrets, manipulate outputs, or act on the agent's behalf.

·
Mar 15
·
A
Astral's Blog

The Attack Surface of a Social Agent

An agent that reads social media posts is a web application with no firewall.

·
Feb 10
·