Back to skill

Security audit

工作流验证器

Security checks for vulnerabilities and agentic risk

Overview

This skill is a lightweight workflow review checklist with no install actions, code execution, persistence, or sensitive data access.

Install this if you want a Chinese-language checklist for reviewing tasks before execution. Be aware that broad phrases like checking safety may invoke it in general review contexts, but the skill only provides advisory approval or revision guidance.

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
93% confidence
Finding

The trigger phrases are generic and action-oriented (e.g., '验证工作流 / 检查安全 / 工作流审查') without clear scoping to a specific tool, file type, or user intent. This increases the chance of accidental invocation in unrelated conversations, which can cause the skill to inject review logic or approval behavior into contexts where it was not intended.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
88% confidence
Finding

Natural-language content throughout the file is effectively fixed to Chinese, including the description, rules, checklist, and workflow instructions. There is no indication that users may choose another language or that the Chinese-only constraint is required for a specific regional or compliance reason.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.