#Blog
- Source: The lethal trifecta for AI agents
- Source: The Dual LLM pattern for building AI assistants that can resist prompt injection
- Source: Prompt injection and jailbreaking are not the same thing
- Source: New prompt injection papers: Agents Rule of Two and The Attacker Moves Second (Willison)
- Source: Markdown exfiltration (Simon Willison tag archive)
- Source: GitHub MCP exploited (Willison link post)