Back to skill

Security audit

SZZG007 Product Analyzer

Security checks for vulnerabilities and agentic risk

Overview

This is a straightforward product marketing analysis skill with no executable payload or hidden high-impact behavior found.

Before installing, be aware that product links, descriptions, images, and optional competitor searches may involve business information; only provide data you are comfortable using for marketing analysis, and adjust the language setting if Chinese output is not desired.

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
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • 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
94% confidence
Finding

The trigger phrases are generic product-discussion requests such as '分析这个产品的卖点' and '提取产品优势', which are likely to appear in normal conversations unrelated to explicit skill invocation. This can cause accidental activation or routing of user content into the skill, leading to unintended processing, incorrect tool selection, or disclosure of business context to components the user did not mean to invoke.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
88% confidence
Finding

The skill sets a fixed output locale via PRODUCT_ANALYZER_LANG=zh-CN without indicating user choice, negotiation, or opt-in. While not a direct code-execution issue, hard-forcing language can create misleading outputs, usability failures, or mishandling of user/business content when the expected language differs, especially in cross-border commerce workflows.

Content

No source excerpt is available for this finding.