Back to skill

Security audit

选址评估清单台

Security checks for vulnerabilities and agentic risk

Overview

This is a simple Chinese restaurant-site evaluation checklist skill with no code, network access, credential use, or persistent behavior.

Installers should understand that this skill provides a decision framework, not verified local market, legal, permit, or financial advice. Users should avoid sharing unnecessary personal data and should verify rent, foot traffic, utilities, permits, and safety constraints with local sources before acting.

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
91% confidence
Finding

The trigger examples include short, generic phrases such as '选址', '开店选址', and '铺位评估' that can overlap with ordinary user requests and cause the skill to activate too broadly. Over-broad activation can route unrelated conversations into this skill unexpectedly, increasing the chance of inappropriate handling of user input or accidental disclosure of business context within the wrong workflow.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
80% confidence
Finding

All user-facing name, description, usage instructions, trigger phrases, and examples are presented only in Chinese, with no indication that users may choose another language. Under the stated policy, forcing a specific language without opt-in can be a natural-language policy violation unless the locale restriction is clearly documented and justified.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.