薪酬社保与人力技能包（免费版）

• Outcome: Pass
• Latest audit: Sep 21, 2026 · 6:55 PM UTC
• Version: 1.0.31

Overview

This is a local payroll and HR worksheet checker that reads user-supplied files and prints findings, with no evidence of network use, persistence, credential access, or destructive behavior.

Install only if you are comfortable running a local Node.js checker over payroll and HR text exports. Treat results as arithmetic/reconciliation assistance, not legal, tax, payroll-policy, audit, or filing approval; pay close attention to checks_not_run and sub_checks_not_run before relying on a clean result.

A.I.G

Vulnerability Patterns

• Skill Instruction Hijacking: Alters the agent's session goals or safety constraints when the skill loads
• Agent Memory Poisoning: Writes attacker-controlled rules into memory that affect later sessions
• Remote Payload Retrieval and Execution: Fetches external code whose behavior can change after review
• Embedded Malicious Code: Ships malicious scripts inside the skill and executes them locally
• Unauthorized Access and Privilege Escalation: Obtains permissions beyond the task's legitimate needs

SkillSpector

Vulnerability Patterns

• MCP Tool Poisoning: Hidden Instructions, Unicode Deception, Parameter Description Injection
• Prompt Injection: Instruction Override, Hidden Instructions, Exfiltration Commands
• Data Exfiltration: External Transmission, Env Variable Harvesting, File System Enumeration
• Privilege Escalation: Excessive Permissions, Sudo/Root Execution, Credential Access
• Supply Chain: Unpinned Dependencies, External Script Fetching, Obfuscated Code

Findings (42)

Tp4

High

• Category: MCP Tool Poisoning
• Confidence: 99% confidence

Finding

The skill markets itself as a complete 14-check payroll/HR verifier that works per client and cites source file plus line, but the evidence indicates the implemented logic only covers narrow subsets or single domains while many advertised checks are withheld or unimplemented. In payroll, tax, and social-insurance workflows, users may rely on the tool to approve payments or filings; a capability gap can therefore create false assurance, causing missed payroll, tax, social-insurance, or compliance errors.

Content

No source excerpt is available for this finding.

Tp4

High

• Category: MCP Tool Poisoning
• Confidence: 99% confidence

Finding

The skill markets itself as a complete 14-check payroll/HR verifier that works per client and cites source file plus line, but the evidence indicates the implemented logic only covers narrow subsets or single domains while many advertised checks are withheld or unimplemented. In payroll, tax, and social-insurance workflows, users may rely on the tool to approve payments or filings; a capability gap can therefore create false assurance, causing missed payroll, tax, social-insurance, or compliance errors.

Content

No source excerpt is available for this finding.

Tp4

High

• Category: MCP Tool Poisoning
• Confidence: 99% confidence

Finding

The skill markets itself as a complete 14-check payroll/HR verifier that works per client and cites source file plus line, but the evidence indicates the implemented logic only covers narrow subsets or single domains while many advertised checks are withheld or unimplemented. In payroll, tax, and social-insurance workflows, users may rely on the tool to approve payments or filings; a capability gap can therefore create false assurance, causing missed payroll, tax, social-insurance, or compliance errors.

Content

No source excerpt is available for this finding.

Tp4

High

• Category: MCP Tool Poisoning
• Confidence: 99% confidence

Finding

The skill markets itself as a complete 14-check payroll/HR verifier that works per client and cites source file plus line, but the evidence indicates the implemented logic only covers narrow subsets or single domains while many advertised checks are withheld or unimplemented. In payroll, tax, and social-insurance workflows, users may rely on the tool to approve payments or filings; a capability gap can therefore create false assurance, causing missed payroll, tax, social-insurance, or compliance errors.

Content

No source excerpt is available for this finding.

Tp4

High

• Category: MCP Tool Poisoning
• Confidence: 99% confidence

Finding

The skill markets itself as a complete 14-check payroll/HR verifier that works per client and cites source file plus line, but the evidence indicates the implemented logic only covers narrow subsets or single domains while many advertised checks are withheld or unimplemented. In payroll, tax, and social-insurance workflows, users may rely on the tool to approve payments or filings; a capability gap can therefore create false assurance, causing missed payroll, tax, social-insurance, or compliance errors.

Content

No source excerpt is available for this finding.

Tp4

High

• Category: MCP Tool Poisoning
• Confidence: 99% confidence

Finding

The skill markets itself as a complete 14-check payroll/HR verifier that works per client and cites source file plus line, but the evidence indicates the implemented logic only covers narrow subsets or single domains while many advertised checks are withheld or unimplemented. In payroll, tax, and social-insurance workflows, users may rely on the tool to approve payments or filings; a capability gap can therefore create false assurance, causing missed payroll, tax, social-insurance, or compliance errors.

Content

No source excerpt is available for this finding.

Tp4

High

• Category: MCP Tool Poisoning
• Confidence: 99% confidence

Finding

The skill markets itself as a complete 14-check payroll/HR verifier that works per client and cites source file plus line, but the evidence indicates the implemented logic only covers narrow subsets or single domains while many advertised checks are withheld or unimplemented. In payroll, tax, and social-insurance workflows, users may rely on the tool to approve payments or filings; a capability gap can therefore create false assurance, causing missed payroll, tax, social-insurance, or compliance errors.

Content

No source excerpt is available for this finding.

Tp4

High

• Category: MCP Tool Poisoning
• Confidence: 99% confidence

Finding

The skill markets itself as a complete 14-check payroll/HR verifier that works per client and cites source file plus line, but the evidence indicates the implemented logic only covers narrow subsets or single domains while many advertised checks are withheld or unimplemented. In payroll, tax, and social-insurance workflows, users may rely on the tool to approve payments or filings; a capability gap can therefore create false assurance, causing missed payroll, tax, social-insurance, or compliance errors.

Content

No source excerpt is available for this finding.

Tp4

High

• Category: MCP Tool Poisoning
• Confidence: 99% confidence

Finding

The skill markets itself as a complete 14-check payroll/HR verifier that works per client and cites source file plus line, but the evidence indicates the implemented logic only covers narrow subsets or single domains while many advertised checks are withheld or unimplemented. In payroll, tax, and social-insurance workflows, users may rely on the tool to approve payments or filings; a capability gap can therefore create false assurance, causing missed payroll, tax, social-insurance, or compliance errors.

Content

No source excerpt is available for this finding.

Tp4

High

• Category: MCP Tool Poisoning
• Confidence: 99% confidence

Finding

The skill markets itself as a complete 14-check payroll/HR verifier that works per client and cites source file plus line, but the evidence indicates the implemented logic only covers narrow subsets or single domains while many advertised checks are withheld or unimplemented. In payroll, tax, and social-insurance workflows, users may rely on the tool to approve payments or filings; a capability gap can therefore create false assurance, causing missed payroll, tax, social-insurance, or compliance errors.

Content

No source excerpt is available for this finding.

Tp4

High

• Category: MCP Tool Poisoning
• Confidence: 99% confidence

Finding

The skill markets itself as a complete 14-check payroll/HR verifier that works per client and cites source file plus line, but the evidence indicates the implemented logic only covers narrow subsets or single domains while many advertised checks are withheld or unimplemented. In payroll, tax, and social-insurance workflows, users may rely on the tool to approve payments or filings; a capability gap can therefore create false assurance, causing missed payroll, tax, social-insurance, or compliance errors.

Content

No source excerpt is available for this finding.

Tp4

High

• Category: MCP Tool Poisoning
• Confidence: 99% confidence

Finding

The skill markets itself as a complete 14-check payroll/HR verifier that works per client and cites source file plus line, but the evidence indicates the implemented logic only covers narrow subsets or single domains while many advertised checks are withheld or unimplemented. In payroll, tax, and social-insurance workflows, users may rely on the tool to approve payments or filings; a capability gap can therefore create false assurance, causing missed payroll, tax, social-insurance, or compliance errors.

Content

No source excerpt is available for this finding.

Tp4

High

• Category: MCP Tool Poisoning
• Confidence: 99% confidence

Finding

The skill markets itself as a complete 14-check payroll/HR verifier that works per client and cites source file plus line, but the evidence indicates the implemented logic only covers narrow subsets or single domains while many advertised checks are withheld or unimplemented. In payroll, tax, and social-insurance workflows, users may rely on the tool to approve payments or filings; a capability gap can therefore create false assurance, causing missed payroll, tax, social-insurance, or compliance errors.

Content

No source excerpt is available for this finding.

Tp4

High

• Category: MCP Tool Poisoning
• Confidence: 99% confidence

Finding

The skill markets itself as a complete 14-check payroll/HR verifier that works per client and cites source file plus line, but the evidence indicates the implemented logic only covers narrow subsets or single domains while many advertised checks are withheld or unimplemented. In payroll, tax, and social-insurance workflows, users may rely on the tool to approve payments or filings; a capability gap can therefore create false assurance, causing missed payroll, tax, social-insurance, or compliance errors.

Content

No source excerpt is available for this finding.

Tp4

High

• Category: MCP Tool Poisoning
• Confidence: 99% confidence

Finding

The skill markets itself as a complete 14-check payroll/HR verifier that works per client and cites source file plus line, but the evidence indicates the implemented logic only covers narrow subsets or single domains while many advertised checks are withheld or unimplemented. In payroll, tax, and social-insurance workflows, users may rely on the tool to approve payments or filings; a capability gap can therefore create false assurance, causing missed payroll, tax, social-insurance, or compliance errors.

Content

No source excerpt is available for this finding.

Ae1

High

• Category: analysis-evasion
• Confidence: 100% confidence

Finding

Referenced artifact was not completely inspected

Content

Scanner excerpt · SKILL.md (reported line 65)May include surrounding context.

md

node scripts/run.mjs --sample # 单客户样例（内置）

Ae1

High

• Category: analysis-evasion
• Confidence: 100% confidence

Finding

Referenced artifact was not completely inspected

Content

Scanner excerpt · SKILL.md (reported line 66)May include surrounding context.

md

node scripts/run.mjs --sample # 单客户样例（内置）

Ae1

High

• Category: analysis-evasion
• Confidence: 100% confidence

Finding

Referenced artifact was not completely inspected

Content

Scanner excerpt · SKILL.md (reported line 67)May include surrounding context.

md

node scripts/run.mjs --sample # 单客户样例（内置）

Ae1

High

• Category: analysis-evasion
• Confidence: 100% confidence

Finding

Referenced artifact was not completely inspected

Content

Scanner excerpt · SKILL.md (reported line 68)May include surrounding context.

md

node scripts/run.mjs --sample # 单客户样例（内置）

Intent-Code Divergence

High

• Category: Not specified by scanner
• Confidence: 98% confidence

Finding

The code and comments indicate that ladder commission verification should run when a ladder input is provided, but no implementation actually performs that recomputation. Because checkCommission is skipped whenever ladder exists, a caller can supply ladder data and suppress normal commission validation, causing incorrect or fraudulent commission rows to pass with fewer checks.

Content

No source excerpt is available for this finding.

Description-Behavior Mismatch

High

• Category: Not specified by scanner
• Confidence: 99% confidence

Finding

The skill metadata promises 14 payroll/HR/social-insurance checks, but this engine explicitly implements only 4 payroll-table checks and labels the rest as unimplemented. This creates a deceptive capability gap: users may rely on the tool for compliance-sensitive validation that never actually occurs, causing missed payroll, tax, or social-insurance errors.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium

• Category: Not specified by scanner
• Confidence: 88% confidence

Finding

The natural-language comments and user-facing descriptions indicate the skill is designed and documented entirely in Chinese, with no mention of language choice or opt-in. Under the policy, forcing a specific language without user choice can be a locale/language policy violation unless clearly justified as region-specific.

Content

No source excerpt is available for this finding.

Description-Behavior Mismatch

Medium

• Category: Not specified by scanner
• Confidence: 91% confidence

Finding

The module advertises withheld or available checking capabilities around ladder commission review, but this free package does not actually perform that verification. In a payroll/HR validation tool, overstating what is checked can create a false sense of assurance and let miscalculated commissions evade review.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium

• Category: Not specified by scanner
• Confidence: 94% confidence

Finding

This JavaScript file contains all user-facing messages, advice, notes, and disclaimers exclusively in Chinese, including error responses and result summaries. Under the stated policy, forcing a specific language without user opt-in is a natural-language locale violation unless the region-specific constraint is clearly documented and justified.

Content

No source excerpt is available for this finding.

Intent-Code Divergence

Medium

• Category: Not specified by scanner
• Confidence: 97% confidence

Finding

The disclaimer states that the tool checks consistency between the wage sheet and special-account payout totals, but this file explicitly withholds that check and only reports totals. In a payroll/compliance workflow, this can mislead users into trusting a control that was not actually performed, causing missed underpayment/overpayment discrepancies and false assurance in a regulated process.

Content

No source excerpt is available for this finding.