Introducing User-Defined Redaction

How to preserve user permissions in API integrations for AI agents and RAG

An architectural overview of preserving User access-control permissions and roles in API integrations for AI agents and RAGs

Hacker guide: MetaMask Delegation Toolkit ERC-7715 actions

Hacker guide to building with ERC-7715 permissions

Indirect Prompt Injection in Web Content Targets AI Agents

Zscaler found sites hiding prompt-injection text to manipulate AI agents into crypto payments

Prismata: A Defense Against Cross-Site Prompt Injection in Autonomous Web Agents

Autonomous web agents promise to automate everyday browsing tasks, but inherit one of the web's oldest attack surfaces. Cross-Site Scripting

MCP Authorization and OAuth 2.1: How AI Agents Authenticate with Remote Servers

A practical guide to MCP's OAuth 2.1 authorization spec — covering PKCE, Protected Resource Metadata, Resource Indicators, Dynamic Client Re

No Safety Without Standards: Defining Protocols for AI Red-Teaming Disclosures