setup-bayarlah

Warn

Audited by Snyk on Nov 16, 2026

Risk Level: MEDIUM
Full Analysis

MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).

  • Third-party content exposure detected (low risk: 0.10). The required workflow polls /upay/v2/query (SKILL.md [26]) and its response includes payer_login and payer_uid, WeChat payer identity strings a paying customer can influence, so the agent ingests outsider-influenced text after fetching a specific order rather than from an unsolicited feed.

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

  • Direct money access detected (medium risk: 0.30). The skill documents direct payment operations: precreate for DuitNow/WeChat QR charges (line 24), WeChat in-browser payment redirect (line 25), and refund/cancel of payments (lines 29, 44). Its main purpose is integration development, which is normally excluded, but the workflow steps also describe the operational payment and refund routes. Under the recall-first override, I treat these as in scope. These are direct operations, not indirect ones. For control, the service-side Upay API requires each call to carry a sign value derived from terminal_sn/terminal_key (lines 35-36). That is a service-validated credential check, not merely an agent-followed instruction, so it plausibly qualifies as independent access control. The skill does not establish a separate human approval step, but none is required for this tier. Severity is therefore medium rather than high, with the development-vs-operational ambiguity noted.

Issues (2)

W011
MEDIUM

Third-party content exposure detected (indirect prompt injection risk).

W009
MEDIUM

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

Audit Metadata
Risk Level
MEDIUM
Analyzed
Nov 16, 2026, 05:13 AM
Issues
2