generate-appworld-code

Fail

Audited by Snyk on Apr 14, 2026

Risk Level: HIGH
Full Analysis

HIGH W007: Insecure credential handling detected in skill instructions.

  • Insecure credential handling detected (high risk: 1.00). The prompt explicitly requires generated code to include plaintext credentials (e.g., username="user@example.com", password="password") and to pass access tokens as literal parameters, forcing the model to output secrets verbatim.

MEDIUM W009: Direct money access capability detected (payment gateways, crypto, banking).

  • Direct money access detected (high risk: 1.00). The skill explicitly includes AppWorld Venmo API calls that perform payments (e.g., apis.venmo.send_payment(access_token=..., recipient_id=..., amount=...)). It also includes friend-management patterns (apis.venmo.add_friend/remove_friend) and login/token usage for Venmo. These are specific payment-related APIs (direct financial execution), not generic tooling. Therefore it grants direct financial execution capability.

Issues (2)

W007
HIGH

Insecure credential handling detected in skill instructions.

W009
MEDIUM

Direct money access capability detected (payment gateways, crypto, banking).

Audit Metadata
Risk Level
HIGH
Analyzed
Apr 14, 2026, 09:50 PM
Issues
2
Security Audit — snyk — generate-appworld-code