mp-sdks

Warn

Audited by Snyk on Mar 19, 2026

Risk Level: MEDIUM
Full Analysis

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

  • Third-party content exposure detected (high risk: 0.80). The skill's README explicitly instructs the agent to fetch live third-party resources—e.g., "Current SDK versions and changelogs" from GitHub (github.com/mercadopago/...) and developer docs ({DOMAIN}/developers/{LANG}/docs/...)—which are public, untrusted web sources the agent is expected to read and that could materially influence behavior.

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

  • Direct money access detected (high risk: 1.00). The skill documents Mercado Pago SDKs — a payment gateway's client and server SDKs. It explicitly references Checkout Bricks, card tokenization (mp.createCardToken, Card Form), payment components (Payment, CardPayment, Wallet), and server-side SDKs that use an ACCESS TOKEN. These are specific, payment-focused APIs/tools designed for processing payments and tokenizing cards (i.e., financial execution flows), not generic utilities. Therefore it grants direct financial execution capability.

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
Mar 19, 2026, 02:54 PM
Issues
2