git-guardrails-claude-code
Pass
Audited by Gen Agent Trust Hub on Aug 26, 2026
Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
- [PRIVILEGE_ESCALATION]: The skill instructions direct the agent to use
chmod +xon the provided scriptscripts/block-dangerous-git.sh. This is a standard procedure to enable execution of the local hook and does not involve escalating system-wide privileges. - [PERSISTENCE_MECHANISMS]: The skill configures a
PreToolUsehook within~/.claude/settings.json(global) or.claude/settings.json(project-specific). This mechanism ensures the security filter remains active across different agent sessions, which is the stated and primary purpose of the skill. - [COMMAND_EXECUTION]: The provided bash script parses JSON input and performs string matching against a list of dangerous git commands. It operates locally and does not execute arbitrary code from external sources or user input.
Audit Metadata