Back to skill

Security audit

多平台返利管家

Security checks for vulnerabilities and agentic risk

Overview

This is a simple rebate-tracking skill description with no bundled code, install script, or hidden behavior found.

Before using a future implemented version, confirm which shopping-platform accounts it connects to, what order data it reads, and whether sync or reminders run only with your approval. The current submitted artifact itself does not include code or hidden installation behavior.

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 (1)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

The trigger list is broad and includes generic terms such as '返利管理', '返利统计', and English aliases that may overlap with normal conversation. This can cause unintended activation of the skill in contexts unrelated to explicit user intent, increasing the chance of inappropriate invocation, unnecessary data handling, or user confusion.

Content

No source excerpt is available for this finding.