new-workspace

Pass

Audited by Gen Agent Trust Hub on Jul 26, 2026

Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill uses mkdir, cp, and git to scaffold a local workspace directory and initialize version control. These are standard operations for the skill's stated purpose of project provisioning.
  • [DATA_EXFILTRATION]: The skill reads identity and locale facts from ~/.claude/CLAUDE.md to personalize the new workspace. While it pushes code to GitHub via the gh CLI, this is an explicit, user-triggered action for project hosting and does not target sensitive system directories beyond the specific workspace created.
  • [COMMAND_EXECUTION]: The skill executes gh repo create to provision remote repositories. This behavior is documented, follows user flags (--private vs --public), and uses the official GitHub CLI tool.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 26, 2026, 03:21 AM
Security Audit — agent-trust-hub — new-workspace