ClawHub
Back to skill

Security audit

DeFi Audit Workflow

Security checks for vulnerabilities and agentic risk

Overview

This is a static DeFi audit checklist skill with visible paid-product promotion, but no hidden execution, persistence, credential access, or destructive behavior.

Installers should know this free audit workflow includes visible promotion for paid Atlas packs. Treat it as a triage checklist, not a substitute for a full smart-contract audit, and verify any candidate findings independently.

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
  • 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
Findings (3)

Description-Behavior Mismatch

Low
Confidence
93% confidence
Finding
The manifest description frames the skill as an exact-match DeFi audit workflow, but the changelog explicitly states a secondary purpose of driving a security ZIP sales funnel. That commercial discovery behavior is reinforced elsewhere in the file and is not part of the stated audit/review functionality.

Context-Inappropriate Capability

Low
Confidence
91% confidence
Finding
The metadata includes explicit 'paid ZIP funnel discovery' use cases and upsell links, which are marketing capabilities rather than audit-workflow capabilities. Promoting external paid products is not an obvious requirement of a skill whose stated purpose is Solidity/EVM security triage and review.

Description-Behavior Mismatch

Low
Confidence
95% confidence
Finding
The manifest description says the skill is for DeFi audit and security review tasks, but the document includes a dedicated upgrade/purchase section positioning the free skill as a discovery layer for paid products. That is a semantic mismatch between the claimed operational purpose and the actual content delivered by the skill.

Static analysis

No suspicious patterns detected.