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
项目开票与回款核对（免费版）
Security checks for vulnerabilities and agentic risk
Overview
This is a local Chinese-language ledger checker that reads user-provided project billing data and does not show hidden network, persistence, credential, or destructive behavior.
Install only if you are comfortable running a local Node script on project billing and collection ledger text. The tool appears to keep data local and has no network behavior, but its guidance and results are mainly in Chinese and the free version intentionally omits several checks that it lists as not run.
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
- 92% confidence
- Finding
This JavaScript skill embeds its descriptive guidance, warnings, and result text entirely in Chinese, including comments that describe expected use and user-facing messages returned by the tool. Under the policy, forcing a specific language without user opt-in is a natural-language policy violation unless the locale restriction is clearly documented and justified, which is not present here.
- Content
Natural-Language Policy Violations
Medium
- Category
- Not specified by scanner
- Confidence
- 94% confidence
- Finding
The user-facing description, usage, errors, and output strings are entirely in Chinese, which imposes a specific language on users. The file does not indicate that Chinese is optional, configurable, or justified as a region-specific constraint, so this is a natural-language locale policy issue.
- Content
Natural-Language Policy Violations
Low
- Category
- Not specified by scanner
- Confidence
- 84% confidence
- Finding
The primary display names, summary, and main descriptions are written entirely in Chinese, and the detailed body of the skill is also Chinese-first. Although an English description field exists, the skill does not state that users can choose their preferred language or locale, which can conflict with language-choice policy expectations.
- Content
Intent-Code Divergence
Low
- Category
- Not specified by scanner
- Confidence
- 89% confidence
- Finding
The inline documentation at L075 describes non-JSON input as '例如直接粘贴的合同全文', implying broader document handling than the rest of the script, which consistently expects a 项目开票与回款台账 with headers. The actual surrounding usage/help text and insufficient-input guidance indicate the skill is intended for ledger/table materials, so this comment misstates the intended input scope.
- Content
Natural-Language Policy Violations
Low
- Category
- Not specified by scanner
- Confidence
- 87% confidence
- Finding
The JSON sample text is entirely in Chinese and provides no indication that language selection is optional or region-specific. Under the policy rules, forcing a specific language without user opt-in can be a natural-language policy violation.
- Content