Security audit

Illegal Dismissal Guide

Security checks for vulnerabilities and agentic risk

Overview

This is a coherent Chinese labor-dismissal guide with a local compensation calculator, and I found no hidden network, credential, persistence, or destructive behavior.

Install this only if you want PRC labor-dismissal guidance in Chinese. Expect to provide sensitive employment and pay details locally, and choose the output directory deliberately because the calculator writes a markdown report there. Treat the legal content and 2023 salary-reference values as informational and verify current local rules with a qualified lawyer or official labor authority before acting.

A.I.G

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

SkillSpector

Vulnerability Patterns

MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access

Findings (5)

Tp4

High

Category: MCP Tool Poisoning
Confidence: 95% confidence
Finding: The declared description presents a broad end-to-end unlawful-termination support skill, including legal analysis, strategy, arbitration request drafting, and evidence guidance. The supplied code implements only one narrow subset of that description: compensation computation and report generation for N/N+1/2N, with work-year calculation and salary-cap rules. There is no code for determining whether a dismissal is lawful, handling scenarios like调岗降薪/不胜任工作/末位淘汰 as legal issue analysis, generating arbitration claims, or assembling evidence lists. The code does not perform suspicious undeclared actions or access unexpected resources; the mismatch is that the declared scope is materially broader than the actual implemented behavior.
Content: No source excerpt is available for this finding.

Undeclared Tool Scope

Medium

Category: MCP Least Privilege
Confidence: 92% confidence
Finding: The skill references local files and a Python script (references/dismissal_guide.md, scripts/calculate_compensation.py) but does not declare any explicit tool scope or permissions. That creates an authorization ambiguity where a runtime may grant broader file read/write capabilities than intended, increasing the risk of unintended filesystem access or misuse if the skill is extended or interpreted permissively.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium

Category: Not specified by scanner
Confidence: 93% confidence
Finding: The manifest description and all user-facing guidance are written entirely in Chinese and present the skill as operating in that language, but there is no statement that users may choose another language or that the Chinese-only scope is a justified regional constraint. Under the policy rule, forcing a specific language without user opt-in is a natural-language policy violation.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium

Category: Not specified by scanner
Confidence: 91% confidence
Finding: This markdown file presents all guidance, templates, and instructions solely in Chinese and does not indicate that the user can choose another language. Under the policy rule for natural-language violations, forcing a specific language without user opt-in is a reportable issue unless a locale-specific justification is clearly documented.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium

Category: Not specified by scanner
Confidence: 91% confidence
Finding: This code file contains natural-language strings for comments, CLI help text, generated report content, and console output exclusively in Chinese. Because it does not provide user opt-in, alternative locale support, or a documented region-specific justification in the file, it constitutes a language/locale policy concern.
Content: No source excerpt is available for this finding.