Back to skill

Security audit

劳动纠纷自检台

Security checks for vulnerabilities and agentic risk

Overview

This is a text-only labor-dispute self-check skill with no code execution, credential access, data exfiltration, or persistence behavior.

This appears safe to install from a security perspective. Users should still treat its output as general preparation help, avoid sharing unnecessary sensitive personal details, and verify legal deadlines or complex cases with official local sources or a qualified professional.

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 are short, common labor-dispute phrases such as '拖欠工资' and '劳动仲裁', which are plausible user utterances outside the exact intended workflow. This can cause the skill to activate in broader contexts than expected, leading to accidental invocation, irrelevant responses, or routing users into this skill when they were asking a general question.

Content

No source excerpt is available for this finding.

Vague Triggers

Low
Category
Not specified by scanner
Confidence
88% confidence
Finding

The natural-language example includes a broad activation phrase that mixes multiple common employment issues in a generic help request. Ambiguous sample phrasing can train or bias invocation toward over-broad matching, increasing unintended activation for ordinary labor-law questions that do not require this specific skill.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.