{"title":"Agent System-Prompt Boundary Enforcement","region":"Global","category":"Security","description":"Maintain the integrity of core instructions against 'Instruction Drift' or user-led prompt hijacking.","lastUpdated":"2026-02-26","steps":["Use unique, non-guessable XML/Markdown delimiters for system boundaries.","Implement 'Instruction Pinning' by repeating core constraints in the message suffix.","Perform a 'Self-Identity Check' every 5 turns to detect role-play drift.","Monitor agent output for 'Instruction Leaking' (echoing system prompt content).","Reset the system context or 'Prune' the conversation if the boundary is breached.","Use a 'Two-Pass' architecture: Plan in one context, Execute in another."],"url":"https://checklist.day/agent-system-prompt-boundary-enforcement"}