Back to skill

Security audit

探店脚本台

Security checks for vulnerabilities and agentic risk

Overview

This is a single markdown skill for drafting restaurant store-visit video scripts and does not request sensitive access or run code.

Installers should be aware this skill may activate on broad food-video or restaurant-promotion phrasing, but its behavior is limited to generating marketing copy and script structure from user-provided details.

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
94% confidence
Finding

The trigger keywords include broad phrases like “美食短视频”, “拍店”, and “餐饮推广”, which can match many ordinary user requests beyond this skill’s narrow purpose. Over-broad activation can cause unintended routing, making the assistant invoke this skill in unrelated contexts and produce inapplicable marketing content or bypass more appropriate specialized skills.

Content

No source excerpt is available for this finding.

Vague Triggers

Low
Category
Not specified by scanner
Confidence
89% confidence
Finding

The natural-language examples include generic expressions such as “按上面的结果改成更简短的版本” and “把这些整理成一张表”, which are common conversational follow-ups not uniquely tied to this skill. If the platform uses examples to help match invocation, these vague phrases can increase accidental triggering or sticky routing into this skill after unrelated prior outputs.

Content

No source excerpt is available for this finding.