skills/garrytan/gstack-browse/gstack/Gen Agent Trust Hub

gstack

Pass

Audited by Gen Agent Trust Hub on Mar 23, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: Skill setup instructions include downloading Bun from bun.sh and cloning the gstack repository from github.com. The /gstack-upgrade skill also performs remote updates via git fetch and git reset from the same GitHub origin. These sources are categorized as well-known technology services and trusted organizations.\n- [COMMAND_EXECUTION]: The suite makes extensive use of the Bash tool to orchestrate a persistent headless Chromium browser daemon using Playwright. It also utilizes dynamic execution in its skill preambles (source <(...)) to run local helper scripts for project-specific configuration.\n- [DATA_EXFILTRATION]: Features an optional, opt-in telemetry system that transmits anonymous usage data (e.g., skill names, execution time, outcome) to a Supabase backend. The implementation includes user-controllable settings via gstack-config to disable all telemetry.\n- [SAFE]: Heuristic detections for destructive commands are false positives. The careful/bin/check-careful.sh script is a security hook intended to monitor and warn the user about potentially harmful shell or SQL commands before they are executed by the agent.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 23, 2026, 04:06 PM