workshop-create

Pass

Audited by Gen Agent Trust Hub on Aug 2, 2026

Risk Level: SAFE
Full Analysis
  • [COMMAND_EXECUTION]: The skill uses git and gh (GitHub CLI) to perform repository status checks and create new repositories. It correctly identifies the owner and manages the clone process using standard shell commands.
  • [SAFE]: The skill implements safety checks to prevent nesting repositories by using git rev-parse --is-inside-work-tree before initialization, ensuring the local file system structure remains clean.
  • [PROMPT_INJECTION]: The skill ingests user-provided data such as workshop names and directory paths for use in shell commands. While this creates a surface for indirect prompt injection, the instructions provide specific naming guidelines (kebab-case) to the agent, and the capabilities used are appropriate for the skill's stated purpose.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 2, 2026, 06:58 PM
Security Audit — agent-trust-hub — workshop-create