Back to skill

Security audit

比价返利雷达

Security checks for vulnerabilities and agentic risk

Overview

This is a simple price-comparison and rebate skill with broad shopping trigger phrases, but no hidden code, persistence, credential access, or destructive behavior.

Install only if you are comfortable with the agent using product names or shopping links to compare prices across marketplaces. Be aware that broad phrases like 'lowest price' may invoke it during general shopping discussions.

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)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The trigger list includes broad everyday phrases such as '最低价', '哪里买最便宜', and '全网比价', which can easily appear in normal shopping conversations and cause unintended activation. In a skill that may search across platforms and process product links, accidental invocation can lead to unnecessary data handling, confusing routing, or actions being taken in the wrong context.

Content

No source excerpt is available for this finding.

Vague Triggers

Low
Category
Not specified by scanner
Confidence
86% confidence
Finding

The skill describes trigger words but does not define a precise activation scope, required user intent, or exclusions for adjacent shopping-related requests. This ambiguity increases the chance of overbroad matching and misrouting, especially because the skill operates in a common consumer domain where many benign queries overlap with its trigger vocabulary.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.