Security audit

室内设计自动预算生成器

Security checks for vulnerabilities and agentic risk

Overview

This skill locally turns a user-provided DXF and a local pricing library into an Excel budget, with no evidence of hidden network access, persistence, or privilege abuse.

Install this if you are comfortable with a local Chinese-language budgeting tool that reads your DXF file and a local standard pricing JSON library, then writes an Excel file. Check the hardcoded pricing-library path before running it, because it may need adjustment for your environment.

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

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

Findings (3)

Vague Triggers

Medium

Confidence: 92% confidence
Finding: The trigger phrases are broad, generic terms such as '生成预算' and '室内设计预算' that are likely to overlap with ordinary user requests. This can cause accidental activation of the skill in contexts where the user did not explicitly intend to invoke it, leading to unintended file-processing or budget-generation workflows.

Natural-Language Policy Violations

Medium

Confidence: 94% confidence
Finding: The file includes its primary description and usage context in Chinese, and the rest of the script’s printed messages and spreadsheet labels are also Chinese-only. Under the policy, forcing a specific language without opt-in is a natural-language policy violation unless the locale restriction is clearly justified, which is not stated here.

Natural-Language Policy Violations

Low

Confidence: 80% confidence
Finding: 整个技能文档仅以中文描述，未说明是否要求输出必须为中文，也未给出语言选择或用户偏好机制。若该技能在执行时默认强制使用单一语言，可能与语言/地区选择需由用户决定的政策要求不一致。

Static analysis

No suspicious patterns detected.