alipay-pay-for-service

Fail

Audited by Snyk on Apr 27, 2026

Risk Level: HIGH
Full Analysis

HIGH W007: Insecure credential handling detected in skill instructions.

  • Insecure credential handling detected (high risk: 1.00). Yes — the skill explicitly requires copying and outputting signed one-time payment URLs (and inserting session IDs into commands) verbatim, which are secret-like tokens that must not be exposed via the LLM output.

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

  • Third-party content exposure detected (high risk: 0.80). The skill explicitly consumes user-/merchant-provided public cashier URLs (e.g., triggers on "cashier*.alipay.com" per SKILL.md header and Step 2) and runs CLI commands that parse and act on the returned CLI/URL content (extracting shortUrl, MEDIA, and deciding next tool calls), so untrusted third‑party content from those public links can materially influence tool use and workflow.

MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).


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

  • Direct money access detected (high risk: 1.00). This skill is explicitly a payment-processing integration for Alipay. It requires installing the official @alipay/agent-payment package and defines concrete CLI commands that perform payment actions: alipay-bot payment-intent (init payment session), alipay-bot check-wallet (wallet/authorization check), alipay-bot submit-payment --payment-link '<收银台链接>' (submit a payment), and alipay-bot query-payment-status -p "" (query payment status). The primary and explicit purpose of the skill is to execute and manage Alipay payment flows (including submitting transactions and handling one-time signed payment URLs). That matches the “Payment Gateways / Send Transaction” criteria for Direct Financial Execution.

Issues (4)

W007
HIGH

Insecure credential handling detected in skill instructions.

W011
MEDIUM

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

W012
MEDIUM

Unverifiable external dependency detected (runtime URL that controls agent).

W009
MEDIUM

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

Audit Metadata
Risk Level
HIGH
Analyzed
Apr 27, 2026, 05:09 AM
Issues
4
Security Audit — snyk — alipay-pay-for-service