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
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
W009
MEDIUMDirect money access capability detected (payment gateways, crypto, banking).
Audit Metadata