dsh-go-guide

Pass

Audited by Gen Agent Trust Hub on Nov 19, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill consists entirely of markdown documentation files and instructions. There is no executable code, script, or configuration that performs network operations, file system modifications, or command execution.\n- [SAFE]: Instructions in SKILL.md implement strong safety constraints, explicitly forbidding the AI from changing app settings, executing commands, or performing actions on the user's phone. It limits the AI's role to providing information and deep links (dshgo://open/...) for user navigation.\n- [SAFE]: The documentation mentions system-level operations (like apk add or SSH commands) and app features (like Android Shell), but these are described as user-facing features or instructions for the user to follow manually, not actions performed by the skill itself.\n- [SAFE]: No obfuscation, prompt injection attempts, or hardcoded credentials were detected in the skill content. External links provided in the documentation point to the author's official GitHub repository or legitimate deep links within the application environment.
Audit Metadata
Risk Level
SAFE
Analyzed
Nov 19, 2026, 01:04 PM