github-auth

Warn

Audited by Gen Agent Trust Hub on Aug 30, 2026

Risk Level: MEDIUMPRIVILEGE_ESCALATIONCOMMAND_EXECUTIONEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
  • [PRIVILEGE_ESCALATION]: The skill executes a diagnostic PowerShell script (setup_check_github.ps1) using the -ExecutionPolicy Bypass flag, which is designed to override system-level security restrictions on script execution.
  • [COMMAND_EXECUTION]: The skill invokes several shell commands, including the GitHub CLI (gh), the Python interpreter, and PowerShell, to conduct environment checks and verify user credentials.
  • [EXTERNAL_DOWNLOADS]: The diagnostic script checks for and suggests installing the requests and openpyxl Python libraries from external registries if they are not detected in the current environment.
  • [INDIRECT_PROMPT_INJECTION]: The skill interpolates environment variables (GH_OWNER, GH_REPO) directly into shell commands for the GitHub API without explicit sanitization or strict boundary markers, creating a surface for potentially malicious environment data to affect command execution.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Aug 30, 2026, 02:26 AM
Security Audit — agent-trust-hub — github-auth