ClawHub
Back to skill

Security audit

Defi Yield Scanner

Security checks for vulnerabilities and agentic risk

Overview

This skill gives DeFi yield-comparison guidance using public protocol data, with no code, persistence, credential use, or hidden execution behavior in the artifact.

Use this as an informational research aid only. Before acting on any yield opportunity, independently verify current APY, smart-contract risk, liquidity, fees, and tax implications, and do not connect wallets or move funds unless you explicitly intend to do so outside the skill.

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
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • 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)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
92% confidence
Finding

The skill description is broad and naturally phrased enough that a host agent may invoke it for loosely related requests about investing, passive income, or crypto opportunities, even when the user did not explicitly ask for this skill. In a financial context, over-broad triggering increases the chance of unsolicited investment-oriented guidance, retrieval of external market data, and inappropriate routing into a high-risk domain.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.