party-skill

Pass

Audited by Gen Agent Trust Hub on Aug 17, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill implements core logic through official WeChat Cloud Functions (wx-server-sdk), adhering to standard development practices for the platform.
  • [SAFE]: Sensitive data operations, such as creating or retrieving party details, are properly scoped to the authenticated user's openid, preventing unauthorized access to other users' data.
  • [INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted user input (e.g., party titles) and interpolates it into success messages. While this is an attack surface, the risk is mitigated by openid-based data isolation and the nature of the skill's primary purpose.
  • [SAFE]: No hardcoded credentials, malicious network redirects, or suspicious external dependencies were found. Mock data in seed.js contains properly masked telephone numbers.
  • [SAFE]: The skill uses structured data for its components and clear instructional boundaries in its MCP metadata.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 17, 2026, 04:59 AM
Security Audit — agent-trust-hub — party-skill