skills/code-with-beto/skills/ship/Gen Agent Trust Hub

ship

Pass

Audited by Gen Agent Trust Hub on Mar 31, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONREMOTE_CODE_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill downloads the @codewithbeto/ship package from the npm registry using bunx to facilitate project scaffolding.
  • [COMMAND_EXECUTION]: Shell commands are used to configure app identity and install necessary dependencies through bun install.
  • [REMOTE_CODE_EXECUTION]: The execution of the @codewithbeto/ship package via bunx involves running code fetched from a remote registry at runtime.
  • [PROMPT_INJECTION]: User-provided inputs for project naming and configuration are interpolated directly into command-line flags.
  • Ingestion points: User values for flags like --name, --app-name, and --bundle-id enter the shell execution context.
  • Boundary markers: No explicit delimiters or instructions are used to prevent the agent from following instructions embedded in these arguments.
  • Capability inventory: The skill can execute subprocesses via bunx and bun.
  • Sanitization: No sanitization or validation of the user-supplied strings is documented before they are passed to the shell.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 31, 2026, 11:56 PM