paystack-disputes
Pass
Audited by Gen Agent Trust Hub on Oct 9, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes external data including customer contact details, dispute IDs, and transaction IDs which are interpolated into API requests to the Paystack service.
- Ingestion points: Input parameters for
paystackRequestcalls throughoutSKILL.md(e.g.,customer_email,disputeId). - Boundary markers: No explicit delimiters or instructions to ignore embedded content are present in the provided documentation.
- Capability inventory: The skill performs network operations via the
paystackRequesthelper method. - Sanitization: The provided snippets do not demonstrate explicit sanitization or validation of the input fields before they are used in API requests.
Audit Metadata