pagbank
Warn
Audited by Snyk on Jul 4, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (medium risk: 0.65). The required runtime workflow for this skill is webhook handling that ingests the raw HTTP request body from PagBank into the agent’s context (via the webhook endpoint), which is outsider-authored free text (external party notification payload) and can enable indirect prompt injection if forwarded to the LLM.
MEDIUM W009: Direct money access capability detected (payment gateways, crypto, banking).
- Direct money access detected (high risk: 1.00). The skill is an integration guide for PagBank's payment platform and explicitly documents APIs and flows that create and move money: e.g., POST /checkouts (checkout/pay flows), Transfer API (fund transfers — "mTLS required"), Split Payments API (distribute funds to receivers), Recurring Payments API (subscriptions/charges), Payment Link, and PagBank Connect (OAuth) for multi-tenant onboarding. These are specific payment/transfer endpoints and protocols (token/mTLS lifecycle, webhook verification, idempotency) intended to execute financial transactions, not generic tooling. 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