paystack-customers
Pass
Audited by Gen Agent Trust Hub on Oct 9, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill has an ingestion surface for untrusted data from external sources.
- Ingestion points: Data returned from Paystack API calls (e.g., List Customers, Fetch Customer) enters the agent context via the
paystackRequesthelper. - Boundary markers: The skill does not explicitly define delimiters for external data or provide warnings to ignore embedded instructions in the documentation snippets.
- Capability inventory: The skill is designed to perform network operations (GET, POST, PUT) to the Paystack API and write customer data based on instructions.
- Sanitization: There is no explicit sanitization or filtering shown for the data returned from the API before it is processed by the agent.
- [DATA_EXPOSURE]: The skill documentation includes fields for highly sensitive data.
- The
Validate Customer Identitysection explicitly handles Bank Verification Numbers (BVN) and bank account numbers. This is consistent with the primary purpose of the Paystack API for financial service compliance in supported regions.
Audit Metadata