#Prompt-Injection
- Source: The lethal trifecta for AI agents
- Source: The Dual LLM pattern for building AI assistants that can resist prompt injection
- Source: The Attacker Moves Second
- Source: Prompt injection and jailbreaking are not the same thing
- Source: Not what you've signed up for (indirect prompt injection)
- Source: New prompt injection papers: Agents Rule of Two and The Attacker Moves Second (Willison)
- Source: Mitigating the risk of prompt injections in browser use (Anthropic)
- Source: Mitigate jailbreaks and prompt injections (Claude docs)
- Source: MCP Security Notification: Tool Poisoning Attacks (Invariant Labs)
- Source: Markdown exfiltration (Simon Willison tag archive)
- Source: Llama Prompt Guard 2 model card
- Source: GitHub MCP exploited (Willison link post)
- Source: Design Patterns for Securing LLM Agents against Prompt Injections
- Source: Defending Against Indirect Prompt Injection Attacks With Spotlighting
- Source: Defeating Prompt Injections by Design (CaMeL)
- Source: Agents Rule of Two (Meta)
- Source: AgentDojo
- Prompt injection
- Lethal trifecta
- Guardrail tooling