base44-sdk
Warn
Audited by Snyk on Feb 17, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 0.80). The skill explicitly allows ingesting public web content into model prompts (e.g., base44.integrations.Core.InvokeLLM with add_context_from_internet which uses Google Search/Maps/News) and can include arbitrary external API responses via base44.integrations.custom.call and public file_urls (UploadFile), so the agent will read/interpret untrusted third-party/user-generated content.
Audit Metadata