init-taro-miniapp

Pass

Audited by Gen Agent Trust Hub on Mar 12, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill performs shell command execution to initialize projects using npx @tarojs/cli init and manages dependencies with npm install. These are standard operations for the intended purpose of project scaffolding.\n- [PROMPT_INJECTION]: The skill exhibits an indirect prompt injection surface by interpolating user-provided project metadata (name and description) into the generated AGENTS.md file, which is designed to guide future AI agents.
  • Ingestion points: User-provided project name and description variables defined in SKILL.md.
  • Boundary markers: Absent; user input is directly embedded into the AGENTS.md template without delimiters or instructions to ignore embedded commands.
  • Capability inventory: Execution of project initialization, dependency installation, and build scripts.
  • Sanitization: No input validation or sanitization is performed on user-provided strings before they are written to the instruction file.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 12, 2026, 07:34 PM