hubspot
Pass
Audited by Gen Agent Trust Hub on Jul 1, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill references official resources from the author, including the "@apideck/unify" Node.js package and OpenAPI specifications hosted on specs.apideck.com. These are confirmed as official vendor assets.
- [SAFE]: Secret management follows industry best practices by utilizing environment variables (e.g., process.env.APIDECK_API_KEY) for authentication tokens instead of hardcoding sensitive credentials.
- [PROMPT_INJECTION]: The skill exhibits an attack surface for indirect prompt injection common to CRM integrations that process external data. Ingestion points: HubSpot contact, company, and deal records. Boundary markers: Not explicitly implemented in the instructional examples. Capability inventory: CRUD operations on CRM entities and network requests through the Apideck Proxy API. Sanitization: Relies on the standard safety filters of the underlying agent.
Audit Metadata