Back to skill

Security audit

canopy-deposits

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed Canopy crypto-deposit integration that uses a remote MCP server to create and check deposit intents, with clear user-control and credential-handling cautions.

Install this only if you intend to use Canopy for merchant crypto deposits and are comfortable connecting an MCP client to Canopy with the payment_intents:create scope. Configure OAuth or secret keys through the client credential system, not chat, and review any deposit intent, destination wallet, network, token, minimum, and fees before asking the agent to create or issue deposit details.

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
  • 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
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep