paystack-charges
Pass
Audited by Gen Agent Trust Hub on Oct 9, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill implements a multi-step flow that relies on processing data returned from the external Paystack API to determine next actions.
- Ingestion points: Data returned from the Paystack API (e.g.,
result.data.status,result.data.reference) is processed in the provided code examples withinSKILL.md. - Boundary markers: There are no explicit delimiters or instructions to treat the API data as untrusted or to ignore instructions embedded within it.
- Capability inventory: The skill utilizes a
paystackRequesthelper to perform network operations, including POST and GET requests to API endpoints. - Sanitization: The skill demonstrates the use of
encodeURIComponentwhen interpolating transaction references into URL paths.
Audit Metadata