Back to skill

Security audit

Rakuten返利助手

Security checks for vulnerabilities and agentic risk

Overview

This is a simple Chinese-language Rakuten cashback helper with no executable code, persistence, credential access, or hidden behavior.

Before installing, understand that this helper is focused on Rakuten cashback information and may activate for broad U.S. or overseas cashback queries; verify any cashback rates, coupons, or links before using them.

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
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (3)

Tp2

High
Category
MCP Tool Poisoning
Confidence
85% confidence
Finding

Mixing characters from multiple Unicode scripts in a single identifier is a common technique to create visually ambiguous tool names.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
83% confidence
Finding

The skill content is entirely in Chinese and does not indicate that users may choose another language or that the skill is intentionally restricted to a Chinese-speaking audience for a documented reason. Under the stated policy, forcing a specific language without opt-in is a natural-language policy concern.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

The trigger list includes broad shopping-related terms like '美国返利' and '海外购物返利' that can match many general commerce queries beyond this specific service. Overly broad activation can cause unintended routing, misleading users into receiving Rakuten-specific output when they did not ask for this tool, and create an opportunity for inappropriate tool invocation in adjacent shopping contexts.

Content

No source excerpt is available for this finding.