Security audit

SaucerSwap Arbitrage

Security checks for vulnerabilities and agentic risk

Overview

This skill is a coherent SaucerSwap arbitrage guide, but it gives unsafe and incomplete mainnet trading instructions that could cause financial loss if followed.

Review this carefully before installing. Do not let an agent use it to trade real funds unless you add explicit confirmation, testnet or dry-run defaults, full route validation, quote freshness checks, fee and slippage accounting, and transaction parameters that enforce minimum output and deadlines.

A.I.G

Vulnerability Patterns

Insecure Skill Coding PracticesFinds exploitable flaws such as hardcoded secrets or command injection
Skill Instruction HijackingAlters the agent's session goals or safety constraints when the skill loads
Agent Memory PoisoningWrites attacker-controlled rules into memory that affect later sessions
Remote Payload Retrieval and ExecutionFetches external code whose behavior can change after review
Embedded Malicious CodeShips malicious scripts inside the skill and executes them locally

Findings (1)

T09 · Insecure Skill Coding Practices

Error

Location: SKILL.md:21
Finding: Unsafe and Incomplete Mainnet Arbitrage Transaction Guidance
Content: View full analysis
Remediation: View remediation

SkillSpector

Vulnerability Patterns

MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code

Findings (3)

Missing User Warnings

Medium

Category: Not specified by scanner
Confidence: 93% confidence
Finding: The skill explicitly advertises executing atomic swaps and arbitrage on mainnet but does not prominently warn that transactions are irreversible and may result in immediate financial loss from slippage, fees, stale quotes, or logic errors. In the context of an agent skill that could be followed operationally, missing risk disclosures makes unsafe execution more likely.
Content: No source excerpt is available for this finding.

Intent-Code Divergence

Medium

Category: Not specified by scanner
Confidence: 94% confidence
Finding: The skill claims to support triangular arbitrage, but the quote function only fetches a single route from tokenA to tokenB and ignores the remaining hop(s). In a trading skill, this can cause users or downstream agents to calculate profitability on incomplete data and execute loss-making swaps under the false assumption that the full arbitrage path was evaluated.
Content: No source excerpt is available for this finding.

Intent-Code Divergence

Low

Category: Not specified by scanner
Confidence: 91% confidence
Finding: The examples are presented as triangular arbitrage paths, but they are only two-token round trips such as USDC → HBAR → USDC, not three-asset cycles. This mislabels the trading strategy and can mislead operators into using incorrect logic, reducing strategy validity and increasing the chance of accidental losses when real funds are used.
Content: No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.