Ae1
High
- Category
- analysis-evasion
- Content
node scripts/run.mjs --sample # 先看样例（样例本身就是一张自洽的对照表）
- Confidence
- 100% confidence
- Finding
- Referenced artifact was not completely inspected
Security audit
建筑工程材料用量与损耗核对（免费版）
Security checks for vulnerabilities and agentic risk
Overview
This is a local Chinese-language construction material table checker with no evidence of network use, persistence, credential access, or hidden behavior.
Use this only for the intended Chinese-language construction material comparison table workflow. It runs locally and does not appear to send data out, but users should still review outputs manually because it performs arithmetic/table consistency checks, not legal, contractual, or on-site factual verification.
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
Vulnerability Patterns
- MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
- 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 (9)
Ae1
High
- Category
- analysis-evasion
- Content
node scripts/run.mjs --sample # 先看样例（样例本身就是一张自洽的对照表）
- Confidence
- 100% confidence
- Finding
- Referenced artifact was not completely inspected
Ae1
High
- Category
- analysis-evasion
- Content
node scripts/run.mjs --sample # 先看样例（样例本身就是一张自洽的对照表）
- Confidence
- 100% confidence
- Finding
- Referenced artifact was not completely inspected
Natural-Language Policy Violations
Medium
- Confidence
- 90% confidence
- Finding
- The file’s natural-language interface, instructions, sample input, labels, and user-facing messages are entirely in Chinese, with no indication that other languages are supported or that the user can opt into this locale. This creates a language/locale policy concern because the skill effectively mandates a specific language for successful use.
Intent-Code Divergence
Medium
- Confidence
- 89% confidence
- Finding
- The header explicitly says this file is the free-tier subset and that the paid implementation is not in this package. However, the code later includes paid-tier concepts in the returned result, such as `checks_withheld`, `over_amount_total`, and a `basis` string defining `超耗金额`, which contradicts the claim that withheld functionality is only descriptive and not implemented here.
Natural-Language Policy Violations
Medium
- Confidence
- 90% confidence
- Finding
- The user-facing description, usage text, prompts, and errors are all written exclusively in Chinese, which imposes a specific language on users. There is no indication that the skill is region-specific or that users can opt into another language, so this is a natural-language locale policy concern.
Description-Behavior Mismatch
Low
- Confidence
- 82% confidence
- Finding
- The manifest describes a free skill focused on six specific material cross-checks, but the returned result also publishes withheld capability lists, out-of-scope lists, and a formula for `超耗金额`. While it does not fully execute the paid checks, this behavior goes beyond simply performing the declared free validations and exposes additional product-tier semantics not necessary for the stated purpose.
Intent-Code Divergence
Low
- Confidence
- 91% confidence
- Finding
- L075 的注释写明“不是 JSON 就当作纯文本材料（例如直接粘贴的合同全文）”，这与文件头、帮助文本和清单描述中反复强调的“材料需用计划与实际消耗对照表（含表头）”不一致。代码实际只是把非 JSON 内容作为 text 传给核对引擎，并未体现对“合同全文”这一不同文档类型的合理支持，属于文档意图与实际技能范围的矛盾表述。
Natural-Language Policy Violations
Low
- Confidence
- 96% confidence
- Finding
- The JSON payload consists entirely of Chinese headers and values in the "text" field, indicating a fixed language/locale presentation. There is no accompanying natural-language indication that users can choose another language or that the Chinese-only format is intentionally limited to a region-specific use case.
Static analysis
No suspicious patterns detected.