wechat-theme-studio

Pass

Audited by Gen Agent Trust Hub on Aug 19, 2026

Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill uses local command execution to validate themes and interact with the service API.\n
  • Details: Executes node scripts/validate-theme.mjs for security checks and uses curl to send data to the remote endpoint.\n- [EXTERNAL_DOWNLOADS]: The skill interacts with an external service required for its core functionality.\n
  • Details: Sends theme data and markdown content to https://doubaoya.com. This is a vendor-owned service intended for theme processing.\n- [PROMPT_INJECTION]: The skill processes user-provided descriptions to build JSON structures, creating a potential indirect prompt injection surface.\n
  • Ingestion points: User descriptions of theme styles in SKILL.md.\n
  • Boundary markers: Strict instructions regarding WeChat compatibility ("Red Lines") and theme schema in SKILL.md.\n
  • Capability inventory: Includes network access (curl) and local script execution (node) as documented in SKILL.md.\n
  • Sanitization: Utilizes scripts/validate-theme.mjs to block unsafe content such as scripts, event handlers, and unauthorized style injections.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 19, 2026, 01:21 PM
Security Audit — agent-trust-hub — wechat-theme-studio