git-release-start

Pass

Audited by Gen Agent Trust Hub on Jul 29, 2026

Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill relies on executing shell commands for git, gh (GitHub CLI), and glab (GitLab CLI). These are used for branch verification, remote API calls to create branches, and local repository management.
  • [PROMPT_INJECTION]: The skill contains an indirect prompt injection surface by reading data (branch names) from remote repositories to determine naming conventions. While a standard part of the workflow, this involves processing external data that could influence subsequent command generation.
  • Ingestion points: Remote branch lists and history retrieved via git branch -r and git ls-remote.
  • Boundary markers: None; the skill uses inferred naming patterns directly in shell command templates.
  • Capability inventory: Execution of shell commands, platform API interactions (POST requests), and local file writing (echo to release-branch).
  • Sanitization: The instructions do not specify validation or escaping for the branch names discovered in history before they are used as arguments in CLI commands.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 29, 2026, 08:47 PM
Security Audit — agent-trust-hub — git-release-start