agent-guardrails-install
Pass
Audited by Gen Agent Trust Hub on Apr 15, 2026
Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
- [COMMAND_EXECUTION]: The skill generates a bash script at
.claude/hooks/stop-guardrails.shand applieschmod +xto enable execution. This is a standard procedure for installing behavioral hooks in the local project environment. - [COMMAND_EXECUTION]: It modifies
.claude/settings.local.jsonto register the script as a 'Stop' hook, ensuring it executes during the agent's lifecycle within that specific project. - [SAFE]: No remote downloads or network operations were identified. The skill utilizes local templates and restricts all file operations to the project's
.claude/directory. - [SAFE]: Analysis of the workflow shows no attempts to access sensitive system paths (e.g.,
.ssh,.aws) or hardcoded credentials.
Audit Metadata