Back to skill

Security audit

竞品分析专家

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed Chinese competitor-analysis workflow that uses public research guidance and does not request privileged access, persistence, credentials, or local data access.

Install this if you want structured Chinese-language competitor analysis. Be aware that it may trigger on broad market-research or product-comparison prompts and will push for web verification of current public data; review cited sources before relying on business recommendations.

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 (3)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The trigger list in the metadata is broad and includes generic business-analysis terms such as 市场调研、商业分析、行业研究 and SWOT分析. This can cause the skill to activate for ordinary analytical requests outside its intended scope, leading to unintended instruction injection into unrelated conversations and reducing user control over tool/skill selection.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

The activation conditions are ambiguous because several conditions are generic or loosely defined, including 产品对比, 市场调研, 行业研究, 替代品, and XX和YY哪个好. In a skill-routing system, ambiguous activation increases the chance of misrouting benign requests into this skill, where it may impose mandatory workflows or web-search requirements that the user did not ask for.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
98% confidence
Finding

The file explicitly sets output language to Chinese only (“中文输出”) and does not indicate that the user can choose another language. This is a natural-language policy concern because it imposes a locale/language constraint without opt-in or documented justification.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.