ClawHub
Back to skill

Security audit

AgentAPI Hub

Security checks for vulnerabilities and agentic risk

Overview

The skill is a disclosed AgentAPI directory guide, but it tells agents how to make real USDC payments through a third-party API without clear user-confirmation or spending controls.

Review before installing if your agent has wallet or payment capabilities. Only use this with explicit per-payment approval, a low-balance wallet, strict spending limits, and care not to send secrets, private code, personal data, or credentials in proxied prompts.

A.I.G

Vulnerability Patterns
  • Insecure Skill Coding PracticesFinds exploitable flaws such as hardcoded secrets or command injection
  • 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
Findings (2)

T09 · Insecure Skill Coding Practices

Error
Location
SKILL.md:23
Finding

Autonomous Cryptocurrency Payments Lack Mandatory Authorization and Transaction Controls

Content
View full analysis
Remediation
View remediation

T09 · Insecure Skill Coding Practices

Warning
Location
SKILL.md:31
Finding

Sensitive Prompt Content May Be Disclosed to a Third-Party Proxy Without Adequate Safeguards

Content
View full analysis
Remediation
View remediation

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 (5)

External Transmission

Medium
Category
Data Exfiltration
Confidence
50% confidence
Finding

Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.

Content

Scanner excerpt · SKILL.md (reported line 15)May include surrounding context.

md
**Website:** https://agentapihub.com  
**Billing API:** https://api.agentapihub.com  
**Docs:** https://api.agentapihub.com/api/docs

## x402 Pay-Per-Use Billing

External Transmission

Medium
Category
Data Exfiltration
Confidence
50% confidence
Finding

Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.

Content

Scanner excerpt · SKILL.md (reported line 33)May include surrounding context.

md
**Website:** https://agentapihub.com  
**Billing API:** https://api.agentapihub.com  
**Docs:** https://api.agentapihub.com/api/docs

## x402 Pay-Per-Use Billing

External Transmission

Medium
Category
Data Exfiltration
Confidence
50% confidence
Finding

Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.

Content

Scanner excerpt · SKILL.md (reported line 47)May include surrounding context.

md
**Website:** https://agentapihub.com  
**Billing API:** https://api.agentapihub.com  
**Docs:** https://api.agentapihub.com/api/docs

## x402 Pay-Per-Use Billing

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The skill explicitly describes a flow where an agent can spend USDC on Base to access APIs, but it does not include an explicit warning that real funds may be spent or require confirmation before payment. In an agent context, this creates a meaningful risk of unintended financial loss if the skill is used automatically or by users who do not realize the payment flow is live.

Content

No source excerpt is available for this finding.

External Transmission

Medium
Category
Data Exfiltration
Confidence
60% confidence
Finding

Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.

Content

Scanner excerpt · SKILL.md (reported line 33)May include surrounding context.

bash
# 1. Initial request returns 402
curl https://api.agentapihub.com/api/gemini/chat/completions \
  -H "Content-Type: application/json" \
  -d '{"model":"gemini-2.0-flash","messages":[{"role":"user","content":"Hello"}]}'

Static analysis

No suspicious patterns detected.