paystack-transfers
Pass
Audited by Gen Agent Trust Hub on Oct 9, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data from an external source (Paystack API responses) and uses it to drive subsequent actions, creating an attack surface for indirect prompt injection.
- Ingestion points: Data enters the agent context through the
paystackRequesthelper inSKILL.md, specifically from endpoints likeGET /transferandPOST /transfer. - Boundary markers: The instructions do not define boundary markers or delimiters to isolate API response data from the agent's internal reasoning or instructions.
- Capability inventory: The skill possesses the capability to perform financial operations, including initiating transfers (
POST /transfer) and finalizing them with OTPs (POST /transfer/finalize_transfer). - Sanitization: There is no evidence of sanitization, escaping, or validation of the data returned from the Paystack API before it is interpolated into subsequent requests or used for decision-making.
Audit Metadata