connector-dev
Pass
Audited by Gen Agent Trust Hub on Sep 16, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill provides development patterns for connectors that ingest data from external APIs.
- Ingestion points: The
dataProcessing.jsandauthentication.jspatterns utilizehttprequest.get()to fetch data from external endpoints. - Boundary markers: No explicit prompt boundary markers are specified, as the skill focus is on programmatic data handling rather than prompt interpolation.
- Capability inventory: The generated code has capabilities for performing network requests and writing processed data to Domo data grids.
- Sanitization: The skill mandates input sanitization (e.g., regex validation for API tokens) and requires HTTP status code verification for all network responses.
- [SAFE]: All code examples demonstrate secure development practices, including programmatic validation of credentials and graceful error handling.
- [SAFE]: No evidence of prompt injection, data exfiltration, obfuscation, or unauthorized access attempts was identified.
Audit Metadata