Ae1
High
- Category
- analysis-evasion
- Confidence
- 100% confidence
- Finding
Referenced artifact was not completely inspected
- Content
md node scripts/run.mjs --sample # 先看样例
Security audit
材料成本差异分摊核对（免费版）
Security checks for vulnerabilities and agentic risk
Overview
This skill is a local, disclosed material-cost variance table checker with no evidence of network use, persistence, credential access, or hidden behavior.
Install only if you are comfortable running a local Node.js checker on material cost variance allocation table data. The skill is mainly designed for Chinese-language tables and does not perform the additional checks listed as withheld or out of scope.
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 (6)
Ae1
High
- Category
- analysis-evasion
- Confidence
- 100% confidence
- Finding
Referenced artifact was not completely inspected
- Content
md node scripts/run.mjs --sample # 先看样例
Natural-Language Policy Violations
Medium
- Category
- Not specified by scanner
- Confidence
- 87% confidence
- Finding
The primary display name, summary, tags, and operative descriptions are all in Chinese, and the usage guidance throughout the document is likewise Chinese. Although an English description exists on L13, the skill does not state that users may choose their preferred language, which can amount to forcing a locale without opt-in.
- Content
Natural-Language Policy Violations
Medium
- Category
- Not specified by scanner
- Confidence
- 94% confidence
- Finding
The file’s user-facing natural-language documentation, examples, labels, advice, and disclaimers are entirely in Chinese, and the expected input schema also uses Chinese column names. There is no indication that users may choose another language or locale, which can violate a policy requiring language choice or opt-in.
- Content
Intent-Code Divergence
Low
- Category
- Not specified by scanner
- Confidence
- 95% confidence
- Finding
The inline documentation states that non-JSON input is treated as '直接粘贴的合同全文', which contradicts the rest of the file and manifest that consistently describe the accepted material as a 材料成本差异分摊核对表 with headers. The implementation itself just wraps arbitrary text into
{ text: stripped }, so the comment actively describes a different business document type than the skill's intended scope.- Content
Natural-Language Policy Violations
Low
- Category
- Not specified by scanner
- Confidence
- 95% confidence
- Finding
The JSON payload consists entirely of Chinese headers and values, indicating a fixed language/locale choice embedded in the skill data. Under the policy rules, forcing a specific language without user choice or a documented justification is a natural-language policy concern.
- Content