lp-integration
Warn
Audited by Snyk on Jul 1, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (medium risk: 0.65). The skill’s runtime flow calls Uniswap’s public LP API endpoints (e.g.,
POST /lp/check_approval,/lp/create,/lp/increase, etc.) and ingests the API’s JSON response fields (includingkycRequiredWarnings.kycUrland other returned transaction/permit data) into the agent context, which is outsider-authored free text from a third-party service.
MEDIUM W009: Direct money access capability detected (payment gateways, crypto, banking).
- Direct money access detected (high risk: 1.00). The skill is explicitly a Uniswap liquidity-provisioning integration that builds on-chain transaction payloads and approval/permit flows. It exposes specific endpoints to create/increase/decrease LP positions and to claim fees, and returns ready-to-sign TransactionRequest objects (and approval transactions / permit payloads) that the application is expected to sign and broadcast. Those are crypto/blockchain financial actions (token transfers, approvals, gas-paying transactions). This is a specific crypto financial execution capability, not a generic tool, so it grants direct financial execution authority.
Issues (2)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
W009
MEDIUMDirect money access capability detected (payment gateways, crypto, banking).
Audit Metadata