ClawHub
Back to skill

Security audit

Morpho Base Operator

Security checks for vulnerabilities and agentic risk

Overview

This is a narrowly scoped Morpho vault-operations workflow, with sensitive key and transaction risks disclosed and mostly constrained by registry checks, external signing, and default execution limits.

Install only if you intend to operate Morpho vault workflows and can keep signing keys isolated. Prefer an external signer or hardware-backed flow, verify the registry and MCP package independently, leave allowMainnetExecution false until explicit operator signoff, and do not use the skill for unregistered markets.

A.I.G

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

SkillSpector

Vulnerability Patterns
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • 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 (1)

Context-Inappropriate Capability

Low
Category
Not specified by scanner
Confidence
77% confidence
Finding

The skill documentation states that users must provide an operator private key locally. Handling private keys is a high-sensitivity capability, and with no manifest available to constrain scope, this capability stands out as broader than ordinary workflow orchestration unless the skill's implementation clearly requires direct transaction signing.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.