agentic-trust-boundaries
CommunityEnforce agent trust boundaries in multi-agent systems.
Software Engineering#multi-agent#orchestration#trust-boundaries#security-review#prompt-injection#handoff-contracts
Authormaruakshay
Version1.0.0
Installs0
System Documentation
What problem does it solve?
Multi-agent systems often struggle with trust transitivity, cross-agent prompt injection, and unsafe delegation that can escalate privileges and undermine orchestration.
Core Features & Use Cases
- Explicit handoff contracts between agents defining task_description, allowed_tools, allowed_data_sources, and trust_level.
- Per-edge authorization checks at execution time to prevent unauthorized tool use or memory access.
- Containment and auditability mechanisms to quarantine misbehaving agents and trace provenance.
Quick Start
Identify the agent graph, label trust boundaries, and implement typed handoff contracts for all agent-to-agent edges.
Dependency Matrix
Required Modules
None requiredComponents
Standard package💻 Claude Code Installation
Recommended: Let Claude install automatically. Simply copy and paste the text below to Claude Code.
Please help me install this Skill: Name: agentic-trust-boundaries Download link: https://github.com/maruakshay/mii-ai-security/archive/main.zip#agentic-trust-boundaries Please download this .zip file, extract it, and install it in the .claude/skills/ directory.
Agent Skills Search Helper
Install a tiny helper to your Agent, search and equip skill from 471,000+ vetted skills library on demand.