wechat-miniapp-reviewer

Pass

Audited by Gen Agent Trust Hub on Aug 19, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADS
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill fetches updated operating rules, rejection criteria, and filing guidelines from official WeChat developer domains, specifically developers.weixin.qq.com.
  • [INDIRECT_PROMPT_INJECTION]: The skill processes project-specific data from the local repository (such as app.json, package.json, and source code) to conduct its review, representing a potential surface for indirect instructions.
  • Ingestion points: Files in the local project repository, including configuration files (app.json, project.config.json, package.json) and source directories (pages/**, components/**), as described in SKILL.md.
  • Boundary markers: The skill does not define specific delimiters or instructions to ignore potential adversarial content within the ingested files.
  • Capability inventory: The skill is limited to providing textual review feedback and does not have capabilities for network exfiltration, writing to the file system, or executing shell commands.
  • Sanitization: No explicit sanitization, validation, or filtering of the repository file content is performed.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 19, 2026, 03:12 AM
Security Audit — agent-trust-hub — wechat-miniapp-reviewer