sponge-wallet

Warn

Audited by Snyk on Jul 9, 2026

Risk Level: MEDIUM
Full Analysis

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

  • Third-party content exposure detected (high risk: 0.75). The required workflow includes a “Paid Services” flow where the agent calls /api/paid/fetch with a url value obtained from /api/discover/{serviceId}, which can lead to the agent ingesting outsider-authored free text from arbitrary web content (web scraping) into the LLM context.

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

  • Direct money access detected (high risk: 1.00). The skill is explicitly a crypto/fiat wallet API and includes endpoints and examples that perform financial actions: token transfers, swaps, bridges, trading orders, payment links, banking (KYC, virtual accounts, off-ramp), storing cards/checkout, and fiat onramps via Stripe/Coinbase. It also documents agent registration and how Clawd can directly call the REST API or MCP server with an API key, which grants programmatic authority to move funds and execute trades. This is direct financial execution capability.

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
Jul 9, 2026, 10:46 PM
Issues
2
Security Audit — snyk — sponge-wallet