create-agent-with-sanity-context

Pass

Audited by Gen Agent Trust Hub on Jun 13, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill uses official Sanity.io domains (api.sanity.io) and trusted packages from the @sanity and @ai-sdk (Vercel) namespaces.
  • [COMMAND_EXECUTION]: Instructions guide the user to use standard Sanity CLI commands for token management (npx sanity tokens add) and function deployment (npx sanity blueprints deploy).
  • [DATA_EXFILTRATION]: Conversation data is collected via sanityInsightsIntegration and stored in the user's own Sanity dataset for analytics. This is a documented feature for improving agent performance.
  • [REMOTE_CODE_EXECUTION]: The skill utilizes Sanity Functions for scheduled tasks. The code for these functions is provided in the reference implementations and is deployed to the user's Sanity environment.
  • [PROMPT_INJECTION]: No malicious prompt injection patterns were detected in the instructions or reference system prompts.
  • [DATA_EXPOSURE]: The skill handles Sanity API tokens for read and write access. It correctly identifies the need for 'Viewer' and 'Editor' roles and provides instructions for secure token management.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 13, 2026, 08:49 PM
Security Audit — agent-trust-hub — create-agent-with-sanity-context