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
差旅费标准与报销核对（免费版）
Security checks for vulnerabilities and agentic risk
Overview
This is a local Chinese travel-expense checking skill with no evidence of network use, persistence, credential access, or hidden execution, though one output disclaimer overstates a withheld check.
This skill is reasonable to install if you want a Chinese-language, local-only checker for copied travel reimbursement tables. Treat it as an arithmetic consistency helper, not a complete finance approval control: the free version explicitly does not run meal-subsidy formula, trip-date, accommodation/transport over-standard, or missing-approval checks, despite one misleading disclaimer sentence.
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
Natural-Language Policy Violations
Medium
- Category
- Not specified by scanner
- Confidence
- 97% confidence
- Finding
The file’s user-facing documentation and messages are entirely written in Chinese, including operational instructions and outputs, but there is no indication that the skill is China-specific or that users can choose another language. Under the stated policy, forcing a specific language without opt-in is a natural-language policy violation.
- Content
Intent-Code Divergence
Medium
- Category
- Not specified by scanner
- Confidence
- 97% confidence
- Finding
The file states that the meal-subsidy formula check is withheld in the free version, but the returned disclaimer says this version checks '伙食补助 = 天数 × 标准'. That mismatch can mislead users into believing a control was executed when it was not, causing false assurance and missed over-limit or inconsistent reimbursements in a finance-review workflow.
- Content
Natural-Language Policy Violations
Medium
- Category
- Not specified by scanner
- Confidence
- 92% confidence
- Finding
The user-facing description, help text, errors, and output are entirely in Chinese, and the file does not indicate that language selection is optional or that the tool is intentionally limited to a Chinese-speaking or region-specific audience. Under the policy, forcing a specific language without user opt-in is a natural-language locale violation.
- Content
Intent-Code Divergence
Low
- Category
- Not specified by scanner
- Confidence
- 96% confidence
- Finding
The comment says non-JSON input is treated as plain-text material such as a '合同全文' (full contract text), which contradicts the surrounding manifest and usage text that consistently describe the accepted material as a travel-expense reimbursement/standard table with headers. The code itself only wraps arbitrary text into a payload and passes it to the travel-check engine, so the comment documents a materially different document type than the skill's intended purpose.
- Content
Natural-Language Policy Violations
Low
- Category
- Not specified by scanner
- Confidence
- 79% confidence
- Finding
The JSON sample content is entirely in Chinese, including field headers and status values, with no indication that the skill is China-specific or that users can choose another language or locale. This can violate the language/locale policy when a skill implicitly enforces one language without opt-in or justification.
- Content