bingx-spot-wallet

Warn

Audited by Snyk on Nov 14, 2026

Risk Level: MEDIUM
Full Analysis

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

  • Third-party content exposure detected (low risk: 0.10). The required workflow reads BingX deposit history (api-reference.md [40-49], including the sender-influenced addressTag field) via the /capital/deposit/hisrec call, which an outsider can only affect by sending a deposit, and that field is memo/tag data rather than readable prose.

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

  • Direct money access detected (medium risk: 0.30). Financial scope: the skill documents a direct withdrawal route. The Quick Reference lists /openApi/wallets/v1/capital/withdraw/apply (POST, Withdraw permission), and the Withdrawal Apply Parameters cover coin, network, address, and amount. The skill also supplies a verbatim signed client (fetchSigned) that accepts any /openApi/... path and POST method, so it can reach that endpoint. The stated workflow says the agent will not submit withdrawals and hands submission to the user in the official console. That does not remove the capability, and under the recall-first rule the endpoint and client are treated as an operational direct route. This is a withdrawal, so it is direct, not indirect.

Control: the route is gated by BingX service-side HMAC authentication, using an API key and secret validated by the service. The skill documents this as the required auth for every endpoint (line 8, Quick Reference "Auth: Yes", and the signing client). Under the access-control evidence standard, validated service API credentials count as a qualifying independent control. Agent-followed "do not submit" instructions do not count, but the service-side credential check does. The direct route therefore has qualifying control, which places it at Medium, not High. Indirect operations and read-only queries do not change the tier.

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
Nov 14, 2026, 04:31 AM
Issues
2