native-to-weapp-vite-wevu-migration

Pass

Audited by Gen Agent Trust Hub on Mar 12, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill possesses an indirect prompt injection surface as it processes untrusted user-provided mini-program source code during the migration process.
  • Ingestion points: Native mini-program source files (js, wxml, wxss, json) provided by the user as described in SKILL.md.
  • Boundary markers: The instructions do not define specific delimiters or instructions to ignore embedded commands in the source code.
  • Capability inventory: The skill generates executable Vue SFC code and suggests running build and test commands like pnpm build and e2e validation (SKILL.md).
  • Sanitization: No input validation or sanitization of the provided source code is mentioned or performed.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 12, 2026, 07:43 PM