Back to skill

Security audit

Social Security Rights

Security checks for vulnerabilities and agentic risk

Overview

This skill is a China social-insurance rights assistant that uses local reference text and a simple calculator script, with no evidence of hidden execution, exfiltration, persistence, or privilege abuse.

Install only if you need China social-insurance rights guidance. Treat its legal and contribution-rate content as informational, verify current local rules with 12333/12348 or a professional, and review any generated calculation report before relying on it.

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
  • 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 (4)

Tp4

High
Category
MCP Tool Poisoning
Confidence
95% confidence
Finding

声明描述的是一个广泛的社保维权辅助技能,重点在查询、研判、维权路径与材料/补偿辅助;而代码只完成其中很窄的一部分,即社保补缴金额和滞纳金的静态计算并输出报告。虽然这与“社保补缴”场景有关,属于描述中的一个子问题,但整体主功能明显比声明狭窄,且若用户相信声明,会预期存在查询、维权分析、材料清单、全国地区支持等能力,这些都未在代码中体现。代码也没有发现额外危险或越权能力,主要问题是声明明显夸大、与实际行为不符。

Content

No source excerpt is available for this finding.

Undeclared Tool Scope

Medium
Category
MCP Least Privilege
Confidence
84% confidence
Finding

The skill references local files and a calculation script, which implies file read capability and potentially file write or code-adjacent execution behavior, but it does not declare any tool scope or allowed-tools restrictions. In an agent environment, missing capability scoping increases the chance of over-privileged execution, unintended file access, or misuse if the agent or surrounding runtime grants broader defaults than expected.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
89% confidence
Finding

This markdown file contains only Chinese-language guidance and does not indicate that the user can request another language or that the skill is intentionally limited to Chinese speakers. Under the policy, forcing a specific language without user opt-in is a natural-language policy concern.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
93% confidence
Finding

Natural-language strings such as the title, argument descriptions, city defaults, and generated report content are all Chinese-only, and the default locale assumption is Beijing/China-specific. The file does not provide any user opt-in or alternative language option, which can violate language/locale policy requirements when no justification is stated.

Content

No source excerpt is available for this finding.