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（样例本身就是一张自洽的工单明细表）
Security audit
汽修配件与工时费结算核对（免费版）
Security checks for vulnerabilities and agentic risk
Overview
This skill is a local, purpose-limited auto repair settlement checker with no evidence of network use, persistence, credential access, or destructive behavior.
Install only if you want a Chinese-language, local Node.js checker for copied auto repair work-order tables. It does not validate whether prices are fair, work was actually performed, or refunds should be issued; it only checks arithmetic and table consistency in the supplied data.
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 (7)
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（样例本身就是一张自洽的工单明细表）
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（样例本身就是一张自洽的工单明细表）
Natural-Language Policy Violations
Medium
- Category
- Not specified by scanner
- Confidence
- 93% confidence
- Finding
The file’s natural-language instructions, examples, labels, and user-facing messages are entirely in Chinese, with no indication that other languages are supported or that the user can choose their preferred language. This creates a locale/language policy issue because the skill effectively enforces a specific language rather than offering opt-in or documenting a justified region-specific constraint.
- Content
Natural-Language Policy Violations
Medium
- Category
- Not specified by scanner
- Confidence
- 96% confidence
- Finding
The file’s user-facing description, usage text, prompts, and output messages are entirely in Chinese, which effectively constrains the skill to a specific language. There is no indication that users may choose another language or that the locale restriction is an intentional, documented policy exception.
- Content
Intent-Code Divergence
Low
- Category
- Not specified by scanner
- Confidence
- 92% confidence
- Finding
The inline documentation says non-JSON input is treated as plain text such as 'directly pasted contract full text', but the skill's stated purpose is narrowly limited to checking auto-repair parts and labor detail sheets. The implementation and surrounding help text are centered on work-order tables, so this comment introduces an intent-level contradiction about acceptable material types.
- Content
Natural-Language Policy Violations
Low
- Category
- Not specified by scanner
- Confidence
- 92% confidence
- Finding
The only natural-language content in this file is a Chinese tabular template, which implies a fixed language/locale for generated or expected data. There is no accompanying indication that Chinese is optional, user-selected, or justified as a region-specific constraint, so it may violate the language/locale policy.
- Content