convex-authz

Pass

Audited by Gen Agent Trust Hub on Apr 1, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTION
Full Analysis
  • [SAFE]: The skill serves as a technical integration guide for the @djpanda/convex-authz library. All described functionalities, such as role-based access control and relationship-based authorization, are standard security features for application development.
  • [EXTERNAL_DOWNLOADS]: The skill instructs users to install the @djpanda/convex-authz package from npm. This package and its associated GitHub repository (dbjpanda/convex-authz) are legitimate vendor resources.
  • [COMMAND_EXECUTION]: Provides instructions for running setup commands via the Convex CLI (npx convex run), which is standard practice for configuring Convex components and scheduled cleanup jobs.
  • [DATA_EXFILTRATION]: No suspicious data handling or exfiltration patterns were identified. The library handles standard authorization identifiers such as userId and tenantId within the context of the Convex platform.
  • [PROMPT_INJECTION]: The skill does not contain any instructions that attempt to override the AI agent's behavior or safety guidelines.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 1, 2026, 09:37 PM