ln-315-review-merge-worker
Pass
Audited by Gen Agent Trust Hub on May 12, 2026
Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
- [COMMAND_EXECUTION]: The skill implements a delegation pattern using a local runner (
agent_runner.mjs) to execute external CLI-based AI advisors (Claude and Codex). This execution is restricted to tools defined in a local configuration registry and is used for analysis and review purposes. - [SAFE]: The skill incorporates a 'Critical Verification' protocol that requires the host agent to independently evaluate and approve any suggestion from delegated agents before it is accepted. No evidence of unauthorized data access, credential exposure, or obfuscation was found throughout the skill's scripts and documentation.
Audit Metadata