jingswap

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

• Third-party content exposure detected (medium risk: 0.30). The skill queries auction state, depositor lists, history, and prices from the Jingswap backend API, which processes user-submitted deposits and auction interactions.

MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).

• Potentially malicious external URL detected (high risk: 0.70). The script fetches runtime configuration and state from https://faktory-dao-backend.vercel.app, an arbitrary and unverified third-party Vercel deployment, which constitutes a weak external operational dependency.

HIGH W008: Secret detected in skill content (API keys, tokens, passwords).

• Secret detected (high risk: 1.00). The string jc_b058d7f2e0976bd4ee34be3e5c7ba7ebe45289c55d3f5e45f666ebc14b7ebfd0 found in jingswap.ts is a hardcoded API key (used for the Jingswap API as JINGSWAP_API_KEY). It is a high-entropy literal secret providing access to a third-party backend service.

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

• Direct money access detected (high risk: 1.00). The skill provides specific capabilities for DeFi operations, token swaps, and financial asset deposits/cancellations (such as depositing STX/sBTC/USDCx and settling auction cycles) using a crypto wallet.