crafter-ship

Pass

Audited by Gen Agent Trust Hub on Aug 14, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill installs the @crafter/cli package globally using npm. This package is the official command-line interface for the Crafter Station platform described in the skill.
  • [COMMAND_EXECUTION]: The agent is instructed to execute shell commands including npm install, crafter login, crafter ship, and crafter publish. These commands are integral to the skill's purpose of automating project submissions.
  • [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted project data by reading files which could contain hidden instructions.
  • Ingestion points: The skill reads README.md, package.json, and crafter.ship.json from the current project directory in SKILL.md.
  • Boundary markers: No explicit delimiters are used when reading these files, though the skill instructions limit the scope of files inspected.
  • Capability inventory: The agent can execute package installation and deployment commands (npm, crafter) as seen in the workflow section of SKILL.md.
  • Sanitization: The skill mentions that the CLI validates metadata against versioned contracts before submission in the workflow section of SKILL.md.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 14, 2026, 03:25 AM
Security Audit — agent-trust-hub — crafter-ship