ClawHub
Back to skill

Security audit

HYRE DeFi Intelligence

Security checks for vulnerabilities and agentic risk

Overview

The skill documents a paid DeFi data API but also includes an unsafe automated trading pattern that could trigger repeated paid calls and token purchases without clear user confirmation.

Review this skill carefully before installing. It should be used only for user-directed DeFi data lookups, not autonomous trading. Require explicit approval before any paid x402 request, repeated polling loop, wallet-address submission, or buy/sell action based on AI-generated signals.

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
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (3)

Missing User Warnings

High
Category
Not specified by scanner
Confidence
97% confidence
Finding

The skill includes a trading bot pattern that recommends polling every 30 seconds, calling paid endpoints, and auto-buying based on AI signals, but it does not include prominent user warnings or consent requirements for automated trading and billable external network use. This is dangerous because users or downstream agents may execute repeated paid requests and financial actions without understanding cost, risk, or the unreliability of model-generated trading signals.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
91% confidence
Finding

The skill description uses very broad trigger phrases such as trading signals, new tokens, whale tracking, and DeFi data, which can match common finance-related user requests and cause over-invocation. In this skill, that risk is amplified because invocation can lead to paid external requests and trading-oriented guidance, increasing the chance of unintended spending or risky financial automation.

Content

No source excerpt is available for this finding.

External Transmission

Medium
Category
Data Exfiltration
Confidence
86% confidence
Finding

The example commands transmit data to an external third-party service at hyreagent.fun, which creates a real data egress path and can incur payment under the documented x402 model. In this context, the risk is heightened because the skill is designed to be broadly triggered and tied to financial decision-making, so even simple example usage can leak user-derived data or generate unexpected charges.

Content

Scanner excerpt · SKILL.md (reported line 70)May include surrounding context.

bash
# Get latest launches
curl -X POST https://hyreagent.fun/trenches/new-tokens \
  -H "Content-Type: application/json" \
  -d '{"limit": 5}'

Static analysis

No suspicious patterns detected.