Security audit

AI Agent Lending - Wallet Credit

Security checks for vulnerabilities and agentic risk

Overview

The skill matches a DeFi lending purpose, but it asks users or agents to sign on-chain borrow, approval, and repayment transactions with a non-expiring borrow permission and limited risk guidance.

Install only if you understand that the examples involve signing blockchain transactions. Verify the network, API provider, contract addresses, token amounts, decimals, and every wallet prompt before signing. Prefer short expirations and minimal limits, and confirm there is a way to revoke or reduce permissions after borrowing or repayment.

A.I.G

Vulnerability Patterns

Unauthorized Access and Privilege EscalationObtains permissions beyond the task's legitimate needs
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)

T05 · Unauthorized Access and Privilege Escalation

Warning

Location: SKILL.md:91
Finding: Non-Expiring Borrow Permission Violates Least Privilege
Content: View full analysis
Remediation: View remediation

SkillSpector

Vulnerability Patterns

Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep

Findings (1)

Missing User Warnings

Medium

Category: Not specified by scanner
Confidence: 97% confidence
Finding: The skill instructs users to perform real on-chain financial actions including granting token approvals, borrowing, and repaying USDC, but it does not prominently warn that these transactions are irreversible, may move funds, and can expose users to financial loss if parameters or contract addresses are wrong. In an agent-skill context, the lack of explicit transaction-risk disclosure is especially dangerous because users may treat the workflow as routine automation and approve spending or debt actions without understanding the consequences.
Content: No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.