ClawHub
Back to skill

Security audit

Morpho market diligence

Security checks for vulnerabilities and agentic risk

Overview

This skill is a Morpho DeFi diligence guide with disclosed read-heavy workflows and guarded, unsigned transaction-preparation guidance only when the user has already requested a write.

Use this for Morpho market or vault diligence, and read any generated transaction sequence carefully before acting. Do not provide private keys or signing authority to the agent; signing and broadcasting should remain an explicit user-controlled wallet action.

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
  • 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 (2)

Description-Behavior Mismatch

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

The skill is presented as evaluation-focused, but it also instructs the agent to prepare unsigned write sequences, simulate real transaction parameters, and verify post-transaction state. That broadens the operational scope from passive analysis into transaction enablement, which can cause unsafe agent behavior, user confusion about authority boundaries, or accidental progression toward fund-moving actions if surrounding controls are weak.

Content

No source excerpt is available for this finding.

Intent-Code Divergence

Low
Category
Not specified by scanner
Confidence
88% confidence
Finding

The compatibility field says 'No signer required,' but later instructions include authorized transaction preparation and receipt verification steps. Even if the skill does not request keys, this mismatch can mislead operators and orchestration systems into treating the skill as strictly read-only when it contains write-adjacent workflow logic.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.