Uniswap Full Lp Workflow

Security checks across malware telemetry and agentic risk

Overview

This is a disclosed Uniswap LP automation skill with real financial risk, but its wallet-impacting actions are purpose-aligned and gated by user confirmations.

Install only if you are comfortable using an agent to prepare real DeFi transactions. Use a limited wallet, verify chain, pool, token addresses, amounts, slippage, approvals, gas, and risk assessment, and do not approve swaps or liquidity entry unless the transaction preview exactly matches your intent.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (2)

Missing User Warnings

Medium
Confidence
95% confidence
Finding
The README explicitly markets the skill as an end-to-end workflow that can autonomously find opportunities, execute swaps, and enter LP positions, but it does not warn that these actions can move user funds or require explicit user confirmation. In a financial-agent context, this omission is dangerous because users may invoke the skill expecting analysis only, while the workflow is framed as capable of executing irreversible on-chain transactions with real financial risk.

Missing User Warnings

Medium
Confidence
97% confidence
Finding
The example prompts directly instruct the agent to open positions, deploy capital, and run the workflow end to end without any accompanying caution about transaction signing, loss risk, approvals, or confirmation gates. Because examples strongly shape operator behavior, these prompts normalize autonomous capital deployment and can lead users to authorize risky or unintended financial actions without understanding the consequences.

VirusTotal

66/66 vendors flagged this skill as clean.

View on VirusTotal