agent-host-chat-contributions

Pass

Audited by Gen Agent Trust Hub on Sep 9, 2026

Risk Level: SAFE
Full Analysis
  • Architectural Documentation: The skill serves as a guide for developers on building 'Agent Host Chat Contributions'. It describes a self-contained behavior model that interacts with an agent's lifecycle hooks.
  • Lifecycle Hook Definitions: The content details various hooks like onIncomingRequest and onOutgoingTurn, providing instructions on how to use them for tasks such as admission gating, command interception, and context injection.
  • Security Best Practices: The documentation emphasizes security-conscious design choices, such as ensuring that admission-gating hooks (like onIncomingRequest) fail closed and are synchronous to prevent state changes during decision-making.
  • Dependency and State Management: It includes guidance on using dependency-injected services and managed mementos for state persistence, discouraging the use of global state or improper cleanup.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 9, 2026, 12:35 PM
Security Audit — agent-trust-hub — agent-host-chat-contributions