Back to skill

Security audit

Screen before you pay

Security checks for vulnerabilities and agentic risk

Overview

The skill is a disclosed payment-screening workflow that fits its stated purpose, with a supply-chain caution around optional unpinned npm/npx helper use.

Install only if you want LION to screen counterparties before x402 payments and are comfortable sending the payTo wallet or related domain to LION and paying the disclosed $0.001/$0.01 checks. If using the npm/npx integrations, pin package versions and review the helper because it runs in a sensitive payment workflow.

Vulnerability Patterns
  • 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
  • Unauthorized Access and Privilege EscalationObtains permissions beyond the task's legitimate needs
Vulnerability Patterns
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (1)

Rp1

Medium
Category
MCP Rug Pull
Confidence
95% confidence
Finding

The skill recommends invoking AgentCash via npx agentcash@latest, which fetches and executes the newest package version at runtime without pinning to a known-good release. If the upstream package is compromised, typo-squatted, or a breaking/malicious update is published, an agent following this guidance could execute untrusted code in a sensitive payment workflow.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.