interswitch-transfers
Pass
Audited by Gen Agent Trust Hub on Mar 13, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill exhibits an indirect prompt injection surface through its handling of external data.
- Ingestion points: The skill ingests potentially untrusted data from the Interswitch API, such as 'accountName' from the name enquiry endpoint and 'responseDescription' from transfer endpoints.
- Boundary markers: The provided implementation lacks explicit delimiters or instructions to prevent the agent from obeying instructions that might be embedded in these external strings.
- Capability inventory: The skill has the capability to initiate single and bulk financial transfers, and query transaction statuses via network requests.
- Sanitization: There is no evidence of sanitization, escaping, or validation of the strings returned from the API before they are presented to the agent or user, which could allow a malicious account name to influence agent behavior.
Audit Metadata