ClawHub
Back to skill

Security audit

skill-alipayplus-integration

Security checks for vulnerabilities and agentic risk

Overview

This skill is a scoped Alipay+ integration helper that fetches official documentation and does not install code, persist itself, or handle credentials unexpectedly.

Install this if you want an agent to help with Alipay+ integration and are comfortable with it making live requests to official Alipay+ documentation. Confirm your ACQP or MPP role and product before relying on generated code or API details, and avoid sharing private keys or production credentials in the chat.

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 (2)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
90% confidence
Finding

The trigger phrases are generic enough to overlap with ordinary payment-related conversation, which can cause the skill to activate unexpectedly outside a clearly scoped invocation pattern. In a payment integration context, unintended activation can expose users to irrelevant external-fetch behavior, broaden the attack surface for prompt injection via fetched docs, and reduce operator control over when the skill runs.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
96% confidence
Finding

The trigger phrases include extremely broad terms such as "Alipay+" and "AlipayPlus", which can cause the skill to activate on casual mentions rather than clear requests for integration help. This increases the chance of unintended invocation and may route users into a network-fetching workflow unexpectedly, which is more risky here because the skill is designed to always fetch external documentation via curl.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.