gsd-help

Pass

Audited by Gen Agent Trust Hub on Mar 28, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill is designed to provide a user guide by reading a local workspace file. No obfuscation, data exfiltration, or malicious instruction overrides were detected.
  • [DATA_EXPOSURE]: The skill accesses a specific local path (/mnt/local-analysis/workspace-hub/.codex/get-shit-done/workflows/help.md) to retrieve documentation. This access is localized to the workspace environment and is necessary for the skill's primary function.
  • [COMMAND_EXECUTION]: The instructions include a mapping section that teaches the agent how to use standard collaboration tools like spawn_agent and request_user_input. These are legitimate platform capabilities for multi-agent workflows and user interaction.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 28, 2026, 07:11 AM