paystack-verification
Pass
Audited by Gen Agent Trust Hub on Oct 9, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill implementation patterns interpolate external data directly into API request URLs, which creates a potential surface for indirect prompt injection or parameter manipulation if inputs are not properly handled.
- Ingestion points: The
accountNumber,bankCode, andexpectedNameparameters in theverifyAccountBeforeTransferfunction and card BIN resolution logic in SKILL.md. - Boundary markers: Absent; user-provided inputs are directly embedded into URL template strings without protective delimiters or instructions.
- Capability inventory: The skill utilizes network communication capabilities to interact with Paystack API endpoints via the
paystackRequesthelper. - Sanitization: Absent; the provided code examples do not include validation, filtering, or escaping of variables before they are used to construct request URLs.
Audit Metadata