project-setup

Pass

Audited by Gen Agent Trust Hub on Apr 28, 2026

Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill executes multiple gh (GitHub CLI) commands and git operations to create repositories, modify API settings for branch protection, and manage organization-level workflow permissions.
  • [EXTERNAL_DOWNLOADS]: Fetches a configuration schema for 'Release Please' from Google's official GitHub repository (googleapis/release-please).
  • [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because user-provided input for repository names and descriptions is interpolated into shell commands.
  • Ingestion points: User-provided <repo-name> and <short description> strings are injected into gh commands in SKILL.md.
  • Boundary markers: No delimiters or safety instructions are used to wrap the user-provided interpolation.
  • Capability inventory: The skill has the capability to execute shell commands (gh, git) and write files to the local filesystem.
  • Sanitization: There is no explicit sanitization or validation of the user-provided input before it is passed to the shell environment.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 28, 2026, 08:49 AM
Security Audit — agent-trust-hub — project-setup