skills/aammo1/sk/ship-it/Gen Agent Trust Hub

ship-it

Pass

Audited by Gen Agent Trust Hub on Sep 10, 2026

Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill utilizes git and gh CLI commands to manage local branches, push code to remote repositories, and interact with GitHub's pull request API.
  • [EXTERNAL_DOWNLOADS]: The skill provides instructions to download and install the official GitHub CLI tool using established system package managers such as brew, winget, and apt if the tool is not detected on the system.
  • [INDIRECT_PROMPT_INJECTION]: The skill is designed to process commit messages from the local repository to automatically generate branch names and pull request descriptions, which is an inherent surface for indirect prompt injection.
  • Ingestion points: Commit history retrieved via git log.
  • Boundary markers: The skill uses a shell heredoc (EOF) to isolate the PR body content from the command execution context.
  • Capability inventory: Access to the local git repository and network operations via the GitHub CLI.
  • Sanitization: The skill explicitly instructs the agent to "Strip special characters" and "lowercase everything" when generating branch names from commit text, mitigating potential command injection risks.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 10, 2026, 09:56 PM