Skills
skills/membranedev/application-skills/hygraph/Gen Agent Trust Hub

hygraph

Pass

Audited by Gen Agent Trust Hub on Apr 2, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: Installs the @membranehq/cli Node.js package, which is the official tool from the skill's author for managing service integrations.
  • [COMMAND_EXECUTION]: Uses the membrane CLI to interact with Hygraph via a secure proxy, handling authentication and action execution without exposing raw tokens to the agent.
  • [SAFE]: No malicious patterns, prompt injections, or unauthorized data access were detected. The skill specifically instructs the agent to let the platform handle credentials server-side, reducing the risk of secret leakage.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 2, 2026, 12:46 AM