Back to skill

Security audit

指标体系设计台

Security checks for vulnerabilities and agentic risk

Overview

This is a simple metric-design guidance skill with no executable code, data access, persistence, or hidden behavior.

Installers should expect this skill to help design business metrics and tracking plans from user-provided context. Review metric definitions and any personal-information tracking plans with the relevant business, data, and compliance owners before using them operationally.

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
95% confidence
Finding

The examples "按上面的结果改成更简短的版本" and "把这些整理成一张表" are generic everyday editing requests with no skill-specific context. As trigger guidance in a markdown skill file, they do not clearly distinguish when this skill should activate versus when a general-purpose writing or formatting skill should handle the request.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
89% confidence
Finding

The skill name, description, parameters, triggers, and examples are entirely presented in Chinese, with no indication that users may choose another language or locale. Under the stated policy, a skill should not implicitly force a specific language unless it is clearly documented as region-specific or offers opt-in choice.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.