canvas-data-fetching
Pass
Audited by Gen Agent Trust Hub on Feb 17, 2026
Risk Level: SAFE
Full Analysis
- [Data Exposure & Exfiltration] (SAFE): The skill uses environment variables (CANVAS_SITE_URL, CANVAS_JSONAPI_PREFIX) for network operations, which is a secure practice. No sensitive file access or credential leaks were detected.
- [Unverifiable Dependencies] (SAFE): References standard, reputable libraries such as 'swr' (maintained by Vercel, a trusted organization) and 'drupal-jsonapi-params'. These are appropriate for the skill's stated purpose.
- [Prompt Injection] (SAFE): No instructions were found that attempt to override system prompts, bypass safety filters, or extract sensitive internal instructions.
- [Indirect Prompt Injection] (SAFE): The skill processes data from an external CMS. While this creates a data ingestion surface, the patterns provided (React/JSX) automatically handle string escaping, and the instructions focus on structured data retrieval rather than processing untrusted natural language instructions.
- [Command Execution] (SAFE): No shell commands, subprocess spawning, or arbitrary code execution patterns are present.
Audit Metadata