write-script-graphql

Pass

Audited by Gen Agent Trust Hub on Aug 18, 2026

Risk Level: SAFE
Full Analysis
  • [COMMAND_EXECUTION]: The skill provides instructions for executing various wmill CLI commands to manage the script lifecycle. These include wmill script preview for local testing, wmill script run for invoking deployed scripts, and wmill generate-metadata for updating input schemas and dependency locks.
  • [REMOTE_CODE_EXECUTION]: The wmill script preview and wmill script run commands facilitate the execution of script code. The instructions explicitly guide the agent to differentiate between local iterations and deployed code based on user intent and to seek confirmation before performing operations that mutate state or execute code.
  • [EXTERNAL_DOWNLOADS]: The wmill generate-metadata command involves resolving and locking script dependencies. The documentation acknowledges that this process may update unpinned dependency versions, which is standard behavior for package managers and lockfile generators.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 18, 2026, 04:44 AM
Security Audit — agent-trust-hub — write-script-graphql