Back to skill

Security audit

Labor Dispute Check

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed China labor-dispute information helper with simplified legal calculators and no hidden data access, persistence, or remote execution behavior.

Install only if you want an informational China labor-law checklist and rough calculator. Do not treat its outputs as legal advice; verify important severance, overtime, probation, and arbitration decisions with a qualified lawyer or local labor bureau, especially because local rules and case facts can change the result.

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
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (7)

Tp4

High
Category
MCP Tool Poisoning
Confidence
99% confidence
Finding

The declared purpose promises substantive functionality for evaluating China labor dispute issues and estimating employee rights. The actual code does not implement any such behavior; it only prints a generic example message and includes comments indicating that real logic is still TODO. This is a material description-behavior mismatch because the primary purpose described is absent from the code provided.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

High
Category
Not specified by scanner
Confidence
93% confidence
Finding

The overtime calculation embeds China-specific legal assumptions such as a 21.75-day divisor, 8-hour day, 150% overtime multiplier, and a 36-hour monthly cap without any locale selection or rule-source metadata. In a skill that estimates employee rights, users may rely on these outputs for real disputes; applying the wrong jurisdiction can materially misstate legal entitlements and cause financial or legal harm.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

High
Category
Not specified by scanner
Confidence
95% confidence
Finding

The probation checker hard-codes region-specific limits based only on contract length and presents the result as valid or invalid, but does not confirm jurisdiction or account for legal exceptions. Because the skill is marketed as checking labor dispute issues and estimating employee rights, this can mislead users into trusting an incorrect compliance determination for the wrong locale or incomplete rule set.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
89% confidence
Finding

The README lists "劳动纠纷咨询" as a usage trigger, which is a very broad phrase meaning labor-dispute consultation. Unlike the more specific example phrases nearby, this wording does not clearly constrain when the skill should activate and could overlap with many general employment-law conversations.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
92% confidence
Finding

The example trigger "劳动纠纷咨询" is very broad and overlaps with a wide range of ordinary requests for general labor-dispute consultation. The file does not provide exclusion conditions or narrower scope constraints for when this skill should activate versus when a more general legal-help skill should handle the request.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
86% confidence
Finding

The manifest description says to 'Use for' a wide list of legal topics, but it does not define specific trigger phrases, activation boundaries, or negative examples. In a manifest file, this broad invocation guidance can overlap with many ordinary employment-law questions and increase the chance of unintended activation.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
95% confidence
Finding

The instruction "Use this structure for Chinese user questions" followed by a required Chinese output template imposes a language-specific response format based on detected input language rather than explicit user choice. This can violate language/locale policy where users should be offered a choice or the constraint should be clearly justified as a regional requirement.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.