paystack-payment-requests
Pass
Audited by Gen Agent Trust Hub on Oct 9, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes user-controllable data through parameters such as
descriptionandline_itemswhen creating or updating payment requests. - Ingestion points: External strings are accepted for
description,line_items[].name, andcustomeridentifiers as shown in the code examples withinSKILL.md. - Boundary markers: The provided implementation examples do not demonstrate the use of delimiters or specific instructions to the agent to treat these inputs as untrusted data.
- Capability inventory: The skill utilizes the
paystackRequesthelper to execute network requests (POST, PUT, GET) to external endpoints. - Sanitization: The implementation relies on
JSON.stringifyfor request bodies andencodeURIComponentfor URL parameters, which ensures structural integrity but does not filter the natural language content for potential instructions targeting the AI agent.
Audit Metadata