git-guardrails
Pass
Audited by Gen Agent Trust Hub on Nov 8, 2026
Risk Level: SAFE
Full Analysis
- [COMMAND_EXECUTION]: The skill uses
subprocess.runinassets/git_guardrails_hook.pyto callgit symbolic-reffor the purpose of identifying the current branch. This is a read-only operation and essential for determining if a branch is protected.\n- [COMMAND_EXECUTION]: The installer scriptscripts/install_guardrails.pyand the testerscripts/guardrail_test.pyusesubprocess.runto execute local scripts and git commands as part of their installation and verification workflows. These are routine operations for a developer tool.\n- [PERSISTENCE]: The skill's primary function is to install hooks into.claude/settings.jsonand.git/hooks/. While this involves modifying configuration files to ensure the guardrail persists across sessions, the behavior is transparently documented and serves its stated safety purpose.\n- [PRIVILEGE_ESCALATION]: The installer useschmodto ensure that the installed hook scripts are executable. This is standard practice for script installation and is limited to the skill's own assets.\n- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted input (the command string the agent intends to run) through thegit_guardrails_hook.pyscript. It usesshlexfor safe tokenization and parsing to avoid common shell injection pitfalls. It follows a 'fail-open' design for unparseable input to ensure user workflow is not unnecessarily disrupted.
Audit Metadata