start
Pass
Audited by Gen Agent Trust Hub on Aug 19, 2026
Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
- [COMMAND_EXECUTION]: The skill utilizes local shell scripts ('scripts/bootstrap-project.sh' and '.agents/hooks/session-start.sh') to automate project setup and session initialization tasks. These scripts operate on local project files and do not perform network activities.
- [SAFE]: The skill explicitly defines and enforces security best practices, such as preventing the display of secrets in environment files and implementing a command-level blocklist for high-risk operations like 'rm -rf' or forced Git pushes.
- [SAFE]: The project templates include configuration for agent environments (e.g., '.claude/settings.json') that restrict the agent's permissions to a defined set of safe operations.
Audit Metadata