ClawHub
Back to skill

Security audit

Yield Strategies

Security checks for vulnerabilities and agentic risk

Overview

This skill is a clearly disclosed DeFi yield helper, but users should treat deposits and withdrawals as real financial actions requiring explicit approval.

Install only if you intend to let the agent use your authenticated fdx wallet workflow for DeFi yield discovery and transactions. Before any deposit or withdrawal, verify the chain, protocol, token, amount, recipient, APY, and risk level yourself; do not treat discovery results as financial advice.

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
95% confidence
Finding

The skill description is broadly scoped and includes generic trigger phrases like earning yield, staking ETH, exploring DeFi, and finding APY, which can match many ordinary finance-related user requests. Because this skill is user-invocable and can perform high-impact wallet actions such as deposits and withdrawals, broad routing increases the chance the agent invokes it in situations where the user only wanted information or comparison, leading to unintended transaction-oriented flows.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.