research

Pass

Audited by Gen Agent Trust Hub on Jun 16, 2026

Risk Level: SAFE
Full Analysis
  • Script Execution Consideration: The skill instructions specify running a 'preflight script' from the user-context configuration when local shell access is available. This is a standard practice for environment initialization in development-oriented tools and is managed within the local skill environment.
  • Internal Data Access: The workflow includes searching internal sources such as Slack, Google Drive, and Jira. This capability is intentional for the purpose of source-grounded research and utilizes established connectors to provide specific, internal product insights.
  • Modular Instruction Following: The skill utilizes 'Critical Overrides' to reference external guidelines and a plugin router. This modular approach is a security best practice as it centralizes safety and routing logic across multiple skills rather than duplicating instructions.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 16, 2026, 06:12 AM
Security Audit — agent-trust-hub — research