sync-opencode

Pass

Audited by Gen Agent Trust Hub on Nov 9, 2026

Risk Level: SAFECOMMAND_EXECUTIONDYNAMIC_EXECUTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill generates command definition files in .opencode/commands/ that utilize the $ARGUMENTS placeholder. The documentation explicitly warns that the target platform (opencode) may execute shell commands if they are passed as arguments, creating a potential command injection surface if untrusted input is provided by the user.
  • [DYNAMIC_EXECUTION]: The skill generates a JavaScript bridge plugin (.opencode/plugins/easy-claude-hooks.js) at runtime by compiling settings from .claude/settings.json. This plugin is designed to intercept platform events and spawn local hook scripts using Node.js built-ins.
  • [SAFE]: The skill implements disable-model-invocation: true, ensuring that the mutating synchronization pipeline is only executed upon explicit user request, preventing autonomous or accidental execution by the AI agent.
Audit Metadata
Risk Level
SAFE
Analyzed
Nov 9, 2026, 01:34 AM