payermax-integration-assistant

Fail

Audited by Snyk on Aug 24, 2026

Risk Level: HIGH
Full Analysis

HIGH W007: Insecure credential handling detected in skill instructions.

  • Insecure credential handling detected (high risk: 1.00). This skill requires the agent to populate and output complete configuration files (including merchant private key, public key, merchantNo, appId, payermax public key, etc.) and to write fetched sandbox credentials into generated code/config, which forces the LLM to handle and emit secret values verbatim.

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

  • Third-party content exposure detected (medium risk: 0.30). The skill’s Phase 1/3 required workflow ingests the outside user’s free-form conversation to infer scenario and choose variants (then may generate docs/code), with no prerequisite that the text be restricted to trusted/first-party sources.

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). The skill is explicitly designed to integrate with a payment gateway (PayerMax) and includes concrete, actionable APIs/tools for creating and managing payments and refunds, configuring merchant credentials, and invoking sandbox/payment-related operations. Examples: it requires implementing and calling endpoints such as /orderAndPay, /refund, /createPaybylink and related query/refund endpoints; it mandates generating a configuration with merchant private keys; and it references sandbox/MCP tools (e.g., get_sandbox_config, sandbox_generate_keypair, sandbox_update_payment_methods, sandbox_trigger_acceptance) to obtain credentials, configure payment methods, and run sandbox operations. These are specific payment-gateway actions (direct financial execution capabilities), not generic-purpose tools.

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
Aug 24, 2026, 05:41 AM
Issues
4
Security Audit — snyk — payermax-integration-assistant