interswitch-customer-insights

Pass

Audited by Gen Agent Trust Hub on Mar 13, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill is vulnerable to indirect prompt injection because it processes data from external API responses without applying sanitization or boundary markers.
  • Ingestion points: Sensitive data is ingested via DemographicsResponse, FinancialHistoryResponse, and FinancialHabitsResponse objects as defined in SKILL.md.
  • Boundary markers: No delimiters or safety instructions are present to prevent the agent from obeying instructions potentially embedded in fields like transaction descriptions or category names.
  • Capability inventory: The skill performs network requests (fetch) to retrieve PII and financial records, which are subsequently used in critical decision-making flows like KYC and risk profiling.
  • Sanitization: The provided TypeScript code snippets lack any form of input validation or content filtering for the data returned by the API endpoints.
  • [SAFE]: The skill follows recommended security patterns by utilizing environment variables (INTERSWITCH_BASE_URL) for API base URLs and referencing an abstracted authentication method (getAuthHeaders), which avoids hardcoded sensitive credentials.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 13, 2026, 03:22 PM