worktree-orchestrator

Pass

Audited by Gen Agent Trust Hub on Jun 15, 2026

Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill uses shell scripts to automate git worktree creation, codebase analysis, and GitHub integration. It utilizes standard Unix tools (git, jq, grep, find) for repository management and results processing.
  • [EXTERNAL_DOWNLOADS]: The skill documentation recommends installing the official GitHub CLI (gh) from a well-known service (GitHub) to facilitate the creation of issues and pull requests based on analysis results.
  • [PROMPT_INJECTION]: The skill exhibits an indirect prompt injection surface in create_issues.sh, which ingests untrusted subagent findings from findings.md to create GitHub issues containing @claude triggers. While there are no boundary markers or sanitization in the issue body construction, this is considered a low-risk architectural characteristic of the orchestration workflow.
  • [SAFE]: No malicious obfuscation, data exfiltration, or credential harvesting patterns were found. The skill operates within the expected scope of a development tool, and all external interactions are directed towards well-known services.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 15, 2026, 09:45 AM
Security Audit — agent-trust-hub — worktree-orchestrator