github-worktree

Pass

Audited by Gen Agent Trust Hub on Aug 14, 2026

Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill executes various system commands including git, powershell, bash, and the cursor editor CLI. It also runs local scripts provided within the skill package to manage worktree creation and file synchronization.
  • [EXTERNAL_DOWNLOADS]: During its operation, the skill performs git fetch to update the local repository from GitHub. It also executes ./gradlew (or gradlew.bat), which typically downloads necessary build dependencies and the Gradle wrapper from remote servers.
  • [PROMPT_INJECTION]: The skill ingests data from GitHub issue titles and labels. These strings are used to derive branch names and issue descriptions. The associated scripts include sanitization logic (e.g., the get_branch_path_name function) to strip or replace characters that could cause formatting issues or command injection before they are used in shell command interpolation.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 14, 2026, 06:41 AM
Security Audit — agent-trust-hub — github-worktree