referral-system

Pass

Audited by Gen Agent Trust Hub on Aug 2, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill functions as a static code generator utilizing local templates defined within the templates.md file. It does not attempt to download external scripts or execute remote code.
  • [SAFE]: No sensitive data exposure or exfiltration vectors were identified. The tool does not access credentials, environment files, or private keys, and the generated code relies on local storage via SwiftData.
  • [SAFE]: The generated ReferralDeepLinkHandler implements input validation (isPlausibleCode) to verify the integrity of data received from external URLs, which helps prevent malformed data processing.
  • [SAFE]: The use of Glob and Grep is limited to project context detection and conflict prevention, which are standard, low-risk operations for development-focused AI skills.
  • [SAFE]: The skill provides clear documentation on App Store guidelines and fraud prevention (self-referral checks, rate limiting), demonstrating a focus on legitimate and safe application development.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 2, 2026, 01:18 PM
Security Audit — agent-trust-hub — referral-system