magicpay

Warn

Audited by Snyk on Oct 7, 2026

Risk Level: MEDIUM
Full Analysis

MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).

  • Third-party content exposure detected (medium risk: 0.30). The required workflow includes reading agent email threads (list_agent_email_threads / read_agent_email_thread) and outsider-submitted incoming mail bodies, which ingest external outsider-authored free text.

MEDIUM W009: Direct money access capability detected (payment gateways, crypto, banking).

  • Direct money access detected (high risk: 0.70). The skill documents direct financial operations including crypto transfers (run_crypto_transfer), x402 purchases (run_x402_payment), checkout sessions (create_checkout_session), and payment execution through MagicPay/MagicCard (SKILL.md:31-36). These operations rely on the MagicPay approval system and remote MCP service capabilities rather than documenting an independent access control check enforced by the execution layer for these routes.

Issues (2)

W011
MEDIUM

Third-party content exposure detected (indirect prompt injection risk).

W009
MEDIUM

Direct money access capability detected (payment gateways, crypto, banking).

Audit Metadata
Risk Level
MEDIUM
Analyzed
Oct 7, 2026, 06:46 AM
Issues
2