project-init

Pass

Audited by Gen Agent Trust Hub on Feb 20, 2026

Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
  • COMMAND_EXECUTION (LOW): The skill utilizes run_in_terminal() to perform project setup tasks such as git init and uv sync. While these are standard operations for a project initializer, executing commands based on user-provided strings (like project_name) presents a surface for command injection if the agent does not sanitize the input.
  • INDIRECT PROMPT INJECTION (LOW): The skill ingests untrusted user data (project_name) and interpolates it directly into shell commands and file paths.
  • Ingestion points: User input for 'project_name'.
  • Boundary markers: Absent in the provided workflow logic.
  • Capability inventory: run_in_terminal(), create_directory(), create_file().
  • Sanitization: No explicit sanitization or validation of the project name is defined in the script.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 20, 2026, 11:33 AM