Back to skill

Security audit

招商竞争区域对比

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed Chinese-language business analysis workflow for comparing regional investment-promotion competitiveness using public data.

Installers should expect the skill to perform public-source regional and policy research and generate a structured Chinese report, potentially including a Word-download style output. Users should verify sourced data and scoring assumptions before relying on the report for policy, investment, or site-selection decisions.

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
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (2)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
89% confidence
Finding

The trigger list includes broad, common business-analysis phrases that can match ordinary user requests and activate the skill outside a narrow, intended context. This increases the chance of inappropriate routing, causing the agent to apply this skill’s rigid workflow, tool usage, and output constraints to unrelated conversations, which can degrade safety, relevance, and user control.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The skill instructs the agent to operate and produce output in Chinese without offering a user-language fallback or negotiation. If auto-invoked for users interacting in other languages, it can reduce transparency and informed use, and may cause users to miss important caveats, sourcing limits, or decision-relevant warnings in the generated analysis.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.