Security audit

装修合同审核

Security checks for vulnerabilities and agentic risk

Overview

This is a markdown-only Chinese renovation contract review skill with no code execution, persistence, or hidden data access, though users should redact sensitive contract details before using it.

Installers should treat this as practical renovation-contract guidance, not legal advice. Before pasting a contract or quote into the assistant, redact names, addresses, phone numbers, ID numbers, bank details, signatures, and any confidential pricing terms where possible.

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

Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code

Findings (6)

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 94% confidence
Finding: The description explicitly claims the skill covers essentially all questions related to renovation contract review, which can cause the router to invoke this skill outside its truly validated scope. Overbroad scope increases misrouting risk, leading the assistant to apply rigid, domain-specific instructions or knowledge sources to adjacent topics such as legal disputes, refunds, or vendor selection where the skill itself says it should not provide legal advice.
Content: No source excerpt is available for this finding.

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 91% confidence
Finding: The trigger list contains short and generic phrases such as '装修合同', '合同审核', and '建委合同', which are likely to match ordinary conversation too broadly. This can cause accidental activation in contexts that only partially relate to the skill, increasing the chance of irrelevant guidance, hidden prompt takeover of nearby conversations, or inappropriate reliance on the skill's constrained knowledge base.
Content: No source excerpt is available for this finding.

Missing User Warnings

Medium

Category: Not specified by scanner
Confidence: 93% confidence
Finding: The document recommends sending full contract text to an AI for review but does not warn users about privacy, confidentiality, or data retention risks. Contracts can contain personal identifiers, financial terms, addresses, phone numbers, signatures, and dispute details, so encouraging upload to third-party AI services may expose sensitive information to external processors or unintended storage.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Low

Category: Not specified by scanner
Confidence: 94% confidence
Finding: This markdown file contains user-facing instructional content only in Chinese, and there is no indication that users can opt into another language or that the skill is intentionally restricted to a Chinese-speaking or region-specific audience. Under the policy rule for language/locale, forcing a specific language without user opt-in is 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: 79% confidence
Finding: Line L009 describes counterparties as “人渣,” and similar hostile phrasing continues elsewhere. This imposes an unnecessarily adversarial tone in the skill content rather than neutrally presenting guidance, which is a natural-language policy concern for organizational content quality.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Low

Category: Not specified by scanner
Confidence: 82% 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 instructional content only in Chinese and does not indicate that the language is optional, selectable, or region-specific.
Content: No source excerpt is available for this finding.