Back to skill

Security audit

竞品分析器 Competitor Analyzer

Security checks for vulnerabilities and agentic risk

Overview

The skill is a coherent competitor-analysis helper, but it may retain sensitive business context and use web/file tools without clear user controls.

Review this skill before installing if your competitor research includes confidential strategy, unreleased product plans, pricing, customer data, or internal documents. Use it with redacted inputs where possible, and avoid enabling persistent memory for sensitive business context unless you are comfortable with later reuse.

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
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (4)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The trigger phrases are broad enough to match common requests like market research, comparisons, or learning about an industry, which can cause the skill to activate outside its intended scope. In practice this can route users into unnecessary web/file-capable workflows, increasing the chance of unintended data collection, persistence, or tool use without clear user expectation.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
90% confidence
Finding

The skill has Read, Write, and WebSearch capabilities, yet it does not warn users that external searches and local report writing may involve sensitive input, generated files, or exposure of proprietary business context. Because the skill is designed for competitive analysis, users are especially likely to provide confidential product plans, target markets, or strategic notes that could be handled by tools without informed consent.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
97% confidence
Finding

The skill explicitly says it will remember user industry, product positioning, prior competitors, and reporting preferences, but provides no notice about retention, scope, or user control. This creates a privacy risk because users may disclose sensitive business strategy or proprietary information without understanding that it may be stored or reused later.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
89% confidence
Finding

All invocation examples and operating instructions are in Chinese, and the skill does not indicate that language is optional or region-specific. Under the language/locale policy, forcing a single language without user opt-in can be a natural-language policy concern unless the restriction is explicitly documented and justified.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.