工程与建筑结算专家

• Outcome: Pass
• Latest audit: Sep 23, 2026 · 9:10 AM UTC
• Version: 1.0.11

Overview

This skill is a local construction-settlement checking tool, and the inspected artifacts support its stated purpose without showing exfiltration, unsafe execution, or deceptive behavior.

Install only if you are comfortable running a local Node.js checker on construction or settlement tables. It appears to stay local, but it creates a small hidden usage-count file in your home directory and its results are calculation/checking aids, not audit, legal, or payment authorization advice.

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 (82)

Tp4

High

• Category: MCP Tool Poisoning
• Confidence: 98% confidence
• Finding: The skill advertises broad coverage across 15 construction/settlement sub-skills, automatic routing from a single pasted table, and strict insufficiency handling, but the static findings consistently indicate the implementation is much narrower and often fixed to a single checker. This is dangerous because users may rely on absent checks, treat incomplete output as comprehensive assurance, and make financial, compliance, or contracting decisions based on false coverage assumptions.

Tp4

High

• Category: MCP Tool Poisoning
• Confidence: 98% confidence
• Finding: The skill advertises broad coverage across 15 construction/settlement sub-skills, automatic routing from a single pasted table, and strict insufficiency handling, but the static findings consistently indicate the implementation is much narrower and often fixed to a single checker. This is dangerous because users may rely on absent checks, treat incomplete output as comprehensive assurance, and make financial, compliance, or contracting decisions based on false coverage assumptions.

Tp4

High

• Category: MCP Tool Poisoning
• Confidence: 98% confidence
• Finding: The skill advertises broad coverage across 15 construction/settlement sub-skills, automatic routing from a single pasted table, and strict insufficiency handling, but the static findings consistently indicate the implementation is much narrower and often fixed to a single checker. This is dangerous because users may rely on absent checks, treat incomplete output as comprehensive assurance, and make financial, compliance, or contracting decisions based on false coverage assumptions.

Tp4

High

• Category: MCP Tool Poisoning
• Confidence: 98% confidence
• Finding: The skill advertises broad coverage across 15 construction/settlement sub-skills, automatic routing from a single pasted table, and strict insufficiency handling, but the static findings consistently indicate the implementation is much narrower and often fixed to a single checker. This is dangerous because users may rely on absent checks, treat incomplete output as comprehensive assurance, and make financial, compliance, or contracting decisions based on false coverage assumptions.

Tp4

High

• Category: MCP Tool Poisoning
• Confidence: 98% confidence
• Finding: The skill advertises broad coverage across 15 construction/settlement sub-skills, automatic routing from a single pasted table, and strict insufficiency handling, but the static findings consistently indicate the implementation is much narrower and often fixed to a single checker. This is dangerous because users may rely on absent checks, treat incomplete output as comprehensive assurance, and make financial, compliance, or contracting decisions based on false coverage assumptions.

Tp4

High

• Category: MCP Tool Poisoning
• Confidence: 98% confidence
• Finding: The skill advertises broad coverage across 15 construction/settlement sub-skills, automatic routing from a single pasted table, and strict insufficiency handling, but the static findings consistently indicate the implementation is much narrower and often fixed to a single checker. This is dangerous because users may rely on absent checks, treat incomplete output as comprehensive assurance, and make financial, compliance, or contracting decisions based on false coverage assumptions.

Tp4

High

• Category: MCP Tool Poisoning
• Confidence: 98% confidence
• Finding: The skill advertises broad coverage across 15 construction/settlement sub-skills, automatic routing from a single pasted table, and strict insufficiency handling, but the static findings consistently indicate the implementation is much narrower and often fixed to a single checker. This is dangerous because users may rely on absent checks, treat incomplete output as comprehensive assurance, and make financial, compliance, or contracting decisions based on false coverage assumptions.

Tp4

High

• Category: MCP Tool Poisoning
• Confidence: 99% confidence
• Finding: The skill advertises broad coverage across 15 construction/settlement sub-skills, automatic routing from a single pasted table, and strict insufficiency handling, but the static findings consistently indicate the implementation is much narrower and often fixed to a single checker. This is dangerous because users may rely on absent checks, treat incomplete output as comprehensive assurance, and make financial, compliance, or contracting decisions based on false coverage assumptions.

Tp4

High

• Category: MCP Tool Poisoning
• Confidence: 98% confidence
• Finding: The skill advertises broad coverage across 15 construction/settlement sub-skills, automatic routing from a single pasted table, and strict insufficiency handling, but the static findings consistently indicate the implementation is much narrower and often fixed to a single checker. This is dangerous because users may rely on absent checks, treat incomplete output as comprehensive assurance, and make financial, compliance, or contracting decisions based on false coverage assumptions.

Tp4

High

• Category: MCP Tool Poisoning
• Confidence: 98% confidence
• Finding: The skill advertises broad coverage across 15 construction/settlement sub-skills, automatic routing from a single pasted table, and strict insufficiency handling, but the static findings consistently indicate the implementation is much narrower and often fixed to a single checker. This is dangerous because users may rely on absent checks, treat incomplete output as comprehensive assurance, and make financial, compliance, or contracting decisions based on false coverage assumptions.

Tp4

High

• Category: MCP Tool Poisoning
• Confidence: 98% confidence
• Finding: The skill advertises broad coverage across 15 construction/settlement sub-skills, automatic routing from a single pasted table, and strict insufficiency handling, but the static findings consistently indicate the implementation is much narrower and often fixed to a single checker. This is dangerous because users may rely on absent checks, treat incomplete output as comprehensive assurance, and make financial, compliance, or contracting decisions based on false coverage assumptions.

Tp4

High

• Category: MCP Tool Poisoning
• Confidence: 98% confidence
• Finding: The skill advertises broad coverage across 15 construction/settlement sub-skills, automatic routing from a single pasted table, and strict insufficiency handling, but the static findings consistently indicate the implementation is much narrower and often fixed to a single checker. This is dangerous because users may rely on absent checks, treat incomplete output as comprehensive assurance, and make financial, compliance, or contracting decisions based on false coverage assumptions.

Tp4

High

• Category: MCP Tool Poisoning
• Confidence: 98% confidence
• Finding: The skill advertises broad coverage across 15 construction/settlement sub-skills, automatic routing from a single pasted table, and strict insufficiency handling, but the static findings consistently indicate the implementation is much narrower and often fixed to a single checker. This is dangerous because users may rely on absent checks, treat incomplete output as comprehensive assurance, and make financial, compliance, or contracting decisions based on false coverage assumptions.

Tp4

High

• Category: MCP Tool Poisoning
• Confidence: 99% confidence
• Finding: The skill advertises broad coverage across 15 construction/settlement sub-skills, automatic routing from a single pasted table, and strict insufficiency handling, but the static findings consistently indicate the implementation is much narrower and often fixed to a single checker. This is dangerous because users may rely on absent checks, treat incomplete output as comprehensive assurance, and make financial, compliance, or contracting decisions based on false coverage assumptions.

Tp4

High

• Category: MCP Tool Poisoning
• Confidence: 98% confidence
• Finding: The skill advertises broad coverage across 15 construction/settlement sub-skills, automatic routing from a single pasted table, and strict insufficiency handling, but the static findings consistently indicate the implementation is much narrower and often fixed to a single checker. This is dangerous because users may rely on absent checks, treat incomplete output as comprehensive assurance, and make financial, compliance, or contracting decisions based on false coverage assumptions.

Tp4

High

• Category: MCP Tool Poisoning
• Confidence: 98% confidence
• Finding: The skill advertises broad coverage across 15 construction/settlement sub-skills, automatic routing from a single pasted table, and strict insufficiency handling, but the static findings consistently indicate the implementation is much narrower and often fixed to a single checker. This is dangerous because users may rely on absent checks, treat incomplete output as comprehensive assurance, and make financial, compliance, or contracting decisions based on false coverage assumptions.

Tp4

High

• Category: MCP Tool Poisoning
• Confidence: 98% confidence
• Finding: The skill advertises broad coverage across 15 construction/settlement sub-skills, automatic routing from a single pasted table, and strict insufficiency handling, but the static findings consistently indicate the implementation is much narrower and often fixed to a single checker. This is dangerous because users may rely on absent checks, treat incomplete output as comprehensive assurance, and make financial, compliance, or contracting decisions based on false coverage assumptions.

Tp4

High

• Category: MCP Tool Poisoning
• Confidence: 98% confidence
• Finding: The skill advertises broad coverage across 15 construction/settlement sub-skills, automatic routing from a single pasted table, and strict insufficiency handling, but the static findings consistently indicate the implementation is much narrower and often fixed to a single checker. This is dangerous because users may rely on absent checks, treat incomplete output as comprehensive assurance, and make financial, compliance, or contracting decisions based on false coverage assumptions.

Tp4

High

• Category: MCP Tool Poisoning
• Confidence: 98% confidence
• Finding: The skill advertises broad coverage across 15 construction/settlement sub-skills, automatic routing from a single pasted table, and strict insufficiency handling, but the static findings consistently indicate the implementation is much narrower and often fixed to a single checker. This is dangerous because users may rely on absent checks, treat incomplete output as comprehensive assurance, and make financial, compliance, or contracting decisions based on false coverage assumptions.

Tp4

High

• Category: MCP Tool Poisoning
• Confidence: 98% confidence
• Finding: The skill advertises broad coverage across 15 construction/settlement sub-skills, automatic routing from a single pasted table, and strict insufficiency handling, but the static findings consistently indicate the implementation is much narrower and often fixed to a single checker. This is dangerous because users may rely on absent checks, treat incomplete output as comprehensive assurance, and make financial, compliance, or contracting decisions based on false coverage assumptions.

Tp4

High

• Category: MCP Tool Poisoning
• Confidence: 98% confidence
• Finding: The skill advertises broad coverage across 15 construction/settlement sub-skills, automatic routing from a single pasted table, and strict insufficiency handling, but the static findings consistently indicate the implementation is much narrower and often fixed to a single checker. This is dangerous because users may rely on absent checks, treat incomplete output as comprehensive assurance, and make financial, compliance, or contracting decisions based on false coverage assumptions.

Tp4

High

• Category: MCP Tool Poisoning
• Confidence: 98% confidence
• Finding: The skill advertises broad coverage across 15 construction/settlement sub-skills, automatic routing from a single pasted table, and strict insufficiency handling, but the static findings consistently indicate the implementation is much narrower and often fixed to a single checker. This is dangerous because users may rely on absent checks, treat incomplete output as comprehensive assurance, and make financial, compliance, or contracting decisions based on false coverage assumptions.

Tp4

High

• Category: MCP Tool Poisoning
• Confidence: 98% confidence
• Finding: The skill advertises broad coverage across 15 construction/settlement sub-skills, automatic routing from a single pasted table, and strict insufficiency handling, but the static findings consistently indicate the implementation is much narrower and often fixed to a single checker. This is dangerous because users may rely on absent checks, treat incomplete output as comprehensive assurance, and make financial, compliance, or contracting decisions based on false coverage assumptions.

Tp4

High

• Category: MCP Tool Poisoning
• Confidence: 98% confidence
• Finding: The skill advertises broad coverage across 15 construction/settlement sub-skills, automatic routing from a single pasted table, and strict insufficiency handling, but the static findings consistently indicate the implementation is much narrower and often fixed to a single checker. This is dangerous because users may rely on absent checks, treat incomplete output as comprehensive assurance, and make financial, compliance, or contracting decisions based on false coverage assumptions.

Tp4

High

• Category: MCP Tool Poisoning
• Confidence: 99% confidence
• Finding: The skill advertises broad coverage across 15 construction/settlement sub-skills, automatic routing from a single pasted table, and strict insufficiency handling, but the static findings consistently indicate the implementation is much narrower and often fixed to a single checker. This is dangerous because users may rely on absent checks, treat incomplete output as comprehensive assurance, and make financial, compliance, or contracting decisions based on false coverage assumptions.

Static analysis

No suspicious patterns detected.