Back to skill

Security audit

返利推广赚手

Security checks for vulnerabilities and agentic risk

Overview

This is a disclosed affiliate/rebate promotion writing and commission-planning skill with no executable code or hidden system access.

Before installing, use this only for legitimate affiliate promotion: disclose rebate or commission relationships, follow each platform's anti-spam and advertising rules, and avoid entering sensitive commission/account data unless you understand where it will be stored or processed.

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
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)

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
91% confidence
Finding

The skill explicitly supports generating rebate links, distributing them across multiple platforms, and tracking commission income, but provides no warnings about compliance, spam risk, affiliate disclosure obligations, or privacy implications of tracking cross-platform earnings data. This omission increases the chance that users will misuse the skill in ways that violate platform rules or expose sensitive commercial data.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The trigger phrases are broad, generic promotional terms such as '分享赚钱' and '佣金管理', which can easily overlap with ordinary user conversations and cause unintended invocation. In a skill that generates rebate promotion content and handles commission workflows, accidental activation could lead to unsolicited marketing output or unintended handling of affiliate-link related tasks.

Content

No source excerpt is available for this finding.