# boundaries
4 articlestagged with “boundaries”
Permission Boundary Bypass
Escalating from limited to elevated permissions in AI agent systems through scope creep, implicit permission inheritance, and capability confusion.
privilege-escalationpermissionsagent-securityboundariesred-teaming
Lab: Delimiter Escape Attacks
Craft payloads that escape delimiter boundaries separating system and user content, testing how models handle broken fences, nested delimiters, and format confusion.
labdelimiter-escapeprompt-injectionboundariesbeginnerhands-on
Lab: Mapping Safety Boundaries
Systematically discover what a language model will and won't do by probing its safety boundaries across multiple categories and documenting the results.
labsafetyboundariesmappingbeginnerhands-on
Agent Permission Boundary Enforcement
Implement fine-grained permission boundaries for LLM agents that limit tool access based on context and user role.
walkthroughsdefenseagent-permissionsboundaries