groove-admin-claude-hooks
Pass
Audited by Gen Agent Trust Hub on Mar 16, 2026
Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
- [COMMAND_EXECUTION]: The skill generates and writes four shell scripts (
daily-end-reminder.sh,git-activity-buffer.sh,block-managed-paths.sh, andversion-check.sh) to the local directory.groove/hooks/claude/and grants them execution permissions viachmod +x. - [COMMAND_EXECUTION]: It modifies the
.claude/settings.jsonconfiguration file to register these scripts as automated hooks that fire during Claude Code lifecycle events (Stop, PostToolUse, PreToolUse, SessionStart). - [COMMAND_EXECUTION]: The configured hooks include calls to local scripts within the
.agents/skills/directory, facilitating communication between modular utility components. - [SAFE]: The generated shell scripts use standard system tools (python3, grep, date) to process local inputs and do not exhibit patterns of data exfiltration or unauthorized remote access.
- [SAFE]: The skill's behavior of script generation and configuration modification is transparently documented and serves the primary function of establishing a deterministic workflow environment.
Audit Metadata