git-guardrails-claude-code
Pass
Audited by Gen Agent Trust Hub on Oct 11, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill's primary function is to implement safety guardrails for Git operations, reducing the risk of accidental data loss or unwanted remote changes.
- [COMMAND_EXECUTION]: The hook script uses
jqto reliably extract command strings from the agent's internal tool inputs. This is a standard and safe method for processing JSON data in a shell environment. - [PERSISTENCE]: The skill modifies the agent's configuration files (
.claude/settings.jsonor~/.claude/settings.json) to register the hook. While this persists the tool's behavior across sessions, it is the intended and documented purpose of the skill and does not represent a malicious persistence mechanism. - [PRIVILEGE_ESCALATION]: The instructions involve using
chmod +xon the skill's own script to allow it to function as a hook. This is a legitimate setup step for local scripts and does not constitute an unauthorized privilege escalation attempt.
Audit Metadata