base44-cli
Warn
Audited by Snyk on Mar 30, 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's workflow includes commands that fetch remote, user-authored agent configurations (e.g., "npx base44 agents pull" described in references/agents-pull.md and the agent schema in SKILL.md), which contain freeform "instructions" that the system may read and that can materially change agent behavior, so it clearly ingests untrusted third-party content from the Base44 backend.
MEDIUM W009: Direct money access capability detected (payment gateways, crypto, banking).
- Direct money access detected (high risk: 1.00). The skill explicitly lists connectors for external services and specifically names "stripe" as a supported connector type (not returned by list-available but treated as supported and provisioned automatically on the server side). Connectors provide OAuth/access tokens for backend functions to call external APIs, and the CLI includes commands to create/push connectors and run pre-authenticated scripts that can invoke backend functions. This is a specific, explicit integration point for a payment gateway (Stripe), which meets the "Payment Gateways" criterion for Direct Financial Execution.
Issues (2)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
W009
MEDIUMDirect money access capability detected (payment gateways, crypto, banking).
Audit Metadata