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
餐饮菜品成本与出品率核对（免费版）
Security checks for vulnerabilities and agentic risk
Overview
This skill is a local restaurant cost/yield table checker that reads user-provided input and does not show hidden network, persistence, credential, or destructive behavior.
Install only if you are comfortable using a Chinese-language local CLI tool for restaurant cost/yield table checks. Review its disclosed free-version limits: it checks table arithmetic, totals, duplicates, blanks, and negative values, but does not validate the truth of source records or run the withheld paid-version checks.
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
- 98% confidence
- Finding
The file’s natural-language comments and user-facing guidance are entirely in Chinese, including the main usage description and warnings. This imposes a specific language/locale expectation without offering any user choice or documenting a justified region-specific constraint.
- Content
Natural-Language Policy Violations
Medium
- Category
- Not specified by scanner
- Confidence
- 98% confidence
- Finding
The user-facing title, usage, arguments, status messages, and help text are all presented exclusively in Chinese throughout the file. This constitutes a language/locale policy issue because the skill imposes a specific language on users without documenting an opt-in or offering an alternative.
- Content
Intent-Code Divergence
Low
- Category
- Not specified by scanner
- Confidence
- 90% confidence
- Finding
The inline documentation says non-JSON input is treated as plain text such as a pasted '合同全文' (full contract text), which conflicts with the skill's stated purpose of checking a restaurant food cost and yield table. The actual surrounding code and usage text expect a table with headers, so this comment describes a different document type than the skill is intended to process.
- Content
Natural-Language Policy Violations
Low
- Category
- Not specified by scanner
- Confidence
- 90% confidence
- Finding
The JSON payload consists entirely of Chinese column headers and values, indicating a fixed language/locale with no natural-language indication of user opt-in or alternative locale support. Under the policy rule, forcing a specific language without user choice can be a locale-policy violation when no justification is documented.
- Content