Security audit

防水避坑指南

Security checks for vulnerabilities and agentic risk

Overview

This is a text-only Chinese waterproofing and renovation guidance skill with some broader renovation content, but it does not request system access, run code, persist itself, or hide unsafe agent behavior.

Install only if you want Chinese-language homeowner guidance about waterproofing and related renovation pitfalls. Treat structural, electrical, gas, legal, and categorical waterproofing recommendations as discussion aids for qualified professionals, not instructions to perform work yourself.

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

Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
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 (20)

Description-Behavior Mismatch

High

Category: Not specified by scanner
Confidence: 99% confidence
Finding: The reference content is about aluminum window selection, soundproofing, and ventilation, which does not match the skill’s declared purpose of waterproofing guidance. This creates a scope-integrity problem: users or downstream agents relying on the skill for waterproofing advice may retrieve irrelevant or misleading content, reducing trust and potentially causing incorrect renovation decisions.
Content: No source excerpt is available for this finding.

Description-Behavior Mismatch

Medium

Category: Not specified by scanner
Confidence: 95% confidence
Finding: The file materially exceeds a waterproofing-focused skill by giving broad balcony renovation, enclosure, and layout-planning advice. In a narrowly scoped home waterproofing skill, this scope creep is dangerous because users may rely on unsupported structural and renovation guidance as if it were vetted domain guidance, increasing the chance of unsafe decisions.
Content: No source excerpt is available for this finding.

Context-Inappropriate Capability

Medium

Category: Not specified by scanner
Confidence: 95% confidence
Finding: The content provides structural alteration guidance about door/window-wall elements, '配重墙', and when adjacent wall sections may be removed. Even though it includes a warning to consult property management and structural professionals, embedding structural modification advice inside a waterproofing skill creates a significant risk that users will treat the guidance as actionable, potentially leading to unsafe demolition or weakening of building elements.
Content: No source excerpt is available for this finding.

Missing User Warnings

Medium

Category: Not specified by scanner
Confidence: 97% confidence
Finding: The markdown explicitly advises that certain balcony configurations do not need any waterproofing and frames waterproofing as unnecessary or outdated. In a waterproofing-focused skill, this is especially dangerous because users are likely to trust the recommendation and omit protective measures, which can result in hidden leakage, moisture intrusion, mold, damage to adjacent interiors, and costly remediation.
Content: No source excerpt is available for this finding.

Description-Behavior Mismatch

Medium

Category: Not specified by scanner
Confidence: 98% confidence
Finding: The manifest says this skill is dedicated to waterproofing topics such as bathroom/kitchen/balcony waterproofing, leak prevention, materials selection, testing, and acceptance. This document instead provides legal rights and dispute-handling guidance for neighbor-caused leaks, load-bearing wall damage, and daylight obstruction, which is outside the described waterproofing-focused workflow.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium

Category: Not specified by scanner
Confidence: 88% confidence
Finding: This markdown skill content forces a specific language/locale for all users through the document text. Under the policy, language constraints should offer user choice or clearly document a justified region-specific requirement, which is not present here.
Content: No source excerpt is available for this finding.

Description-Behavior Mismatch

Medium

Category: Not specified by scanner
Confidence: 97% confidence
Finding: The file substantially expands beyond the declared waterproofing-focused skill scope into broad electrical and plumbing renovation advice, including wiring, demolition sequencing, and construction decision guidance. Scope drift is dangerous because an agent may present out-of-domain home-renovation guidance as if it were covered by the skill’s expertise, increasing the chance of unsafe or misleading recommendations in higher-risk areas like electrical work and structural modifications.
Content: No source excerpt is available for this finding.

Description-Behavior Mismatch

Medium

Category: Not specified by scanner
Confidence: 96% confidence
Finding: The file content materially deviates from the skill’s stated purpose: instead of being narrowly focused on waterproofing guidance, it contains broad old-house renovation trends, cost-saving advice, demolition notes, and general acceptance standards. This mismatch can cause the agent to retrieve and present out-of-scope advice, increasing the chance of unsafe or misleading recommendations in a construction context where users may rely on the skill for specialized waterproofing decisions.
Content: No source excerpt is available for this finding.

Description-Behavior Mismatch

Medium

Category: Not specified by scanner
Confidence: 97% confidence
Finding: The file materially deviates from the skill's declared scope of a dedicated waterproofing guide and instead contains broad renovation advice covering demolition, contracts, supervision, payment, and general装修“避坑” claims. This scope mismatch is dangerous because an agent may retrieve and present irrelevant or overbroad guidance as authoritative防水 advice, increasing the chance of unsafe or misleading recommendations in a construction context.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Low

Category: Not specified by scanner
Confidence: 90% confidence
Finding: The instruction says responses should use the '西安装修课堂' tone and avoid an AI style, which imposes a specific linguistic/locale presentation by default. This is a natural-language policy concern because the file does not indicate any user choice or opt-in for that stylistic or regional voice.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Low

Category: Not specified by scanner
Confidence: 95% confidence
Finding: SQP-3 applies to all file types and covers natural-language policy violations such as forcing a specific language without user opt-in. This file presents all guidance exclusively in Chinese and contains no indication that users may choose another language or that the locale restriction is explicitly justified.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Low

Category: Not specified by scanner
Confidence: 97% confidence
Finding: This markdown file contains user-facing instructional content exclusively in Chinese, and there is no indication that the skill is region-specific or that users can opt into this language. Under the policy, forcing a specific language without user choice can be a natural-language policy violation.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Low

Category: Not specified by scanner
Confidence: 96% confidence
Finding: SQP-3 applies to all file types and covers language or locale policy violations. This markdown content forces a specific language throughout the skill content, with no opt-in, alternative language, or documented justification for a Chinese-only constraint.
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 user-facing guidance only in Chinese, with no indication that the skill is intentionally region-specific or that alternative language options exist. Under the policy rule for language or locale constraints, forcing a specific language without user opt-in can be a natural-language policy violation.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Low

Category: Not specified by scanner
Confidence: 93% confidence
Finding: The file presents all instructional content in Chinese and does not indicate that other languages are available or that the language choice is optional. Under the policy rule for natural-language violations, forcing a specific language without user opt-in is in scope.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Low

Category: Not specified by scanner
Confidence: 94% confidence
Finding: SQP-3 applies to all file types and covers language or locale policy violations. This file presents all guidance exclusively in Chinese and does not indicate any user opt-in, alternative language availability, or justified region-specific constraint.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Low

Category: Not specified by scanner
Confidence: 95% confidence
Finding: This markdown file uses only Chinese-language content and does not mention that the skill is intended specifically for Chinese-speaking users or a China-specific context. Under the policy rule for language or locale constraints, forcing a single language without user opt-in can be a natural-language policy issue.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Low

Category: Not specified by scanner
Confidence: 90% confidence
Finding: This markdown file is entirely written in Chinese and provides no indication that other languages or locales are supported. Under the stated policy, forcing a specific language without user opt-in is a natural-language policy concern unless the locale restriction is clearly documented and justified.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Low

Category: Not specified by scanner
Confidence: 80% confidence
Finding: This markdown file contains user-facing natural language exclusively in Chinese, with no opt-in, alternative language option, or justification for the language constraint. Under the stated policy, forcing a specific language without user choice can be a natural-language policy violation.
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 is entirely written in Chinese and does not indicate that language selection is optional or that the skill is intentionally limited to a Chinese-speaking or region-specific audience. Under the policy rule for natural-language violations, forcing a specific language without user opt-in can be a locale-policy issue.
Content: No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.