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 +x on the provided script scripts/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 PreToolUse hook 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
Risk Level
SAFE
Analyzed
Aug 26, 2026, 04:25 PM
Security Audit — agent-trust-hub — git-guardrails-claude-code