Ae1
High
- Category
- analysis-evasion
- Content
node scripts/run.mjs --sample # 先看样例
- Confidence
- 100% confidence
- Finding
- Referenced artifact was not completely inspected
Security audit
货运破损理赔与扣款核对（免费版）
Security checks for vulnerabilities and agentic risk
Overview
The skill is a local freight-claim checking tool with no network, persistence, or data-changing behavior, though users should note one runtime disclaimer overstates a total-row check that the free version does not perform.
Install only if you are comfortable running a local Node-based checker on freight claim tables. Treat its output as arithmetic/table-consistency assistance, not a complete audit: the free version does not perform total-row reconciliation or contract/legal validation, despite one runtime disclaimer wording that could imply otherwise.
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
- Content
node scripts/run.mjs --sample # 先看样例
- Confidence
- 100% confidence
- Finding
- Referenced artifact was not completely inspected
Ae1
High
- Category
- analysis-evasion
- Content
node scripts/run.mjs --sample # 先看样例
- Confidence
- 100% confidence
- Finding
- Referenced artifact was not completely inspected
Natural-Language Policy Violations
Medium
- Confidence
- 95% confidence
- Finding
- This JavaScript file's natural-language interface is entirely in Chinese, including warnings, instructions, findings, and result text, but it does not offer any user language selection or state that the skill is intentionally limited to a Chinese-speaking or China-specific environment. Under the policy, forcing a specific language without user opt-in is a natural-language policy violation.
Intent-Code Divergence
Medium
- Confidence
- 98% confidence
- Finding
- The disclaimer states the tool checks total-row reconciliation ('合计行各列 = 各明细行逐列相加'), but this free-version code does not actually implement that validation. This is dangerous because users may rely on a claimed control that is absent, causing material accounting discrepancies or over/under-deductions to go undetected in a financial reconciliation workflow.
Natural-Language Policy Violations
Medium
- Confidence
- 94% confidence
- Finding
- All user-facing documentation, usage text, status messages, and prompts in this file are written only in Chinese, including help output and error handling. The file does not state that the skill is region-specific or provide any user opt-in or alternative locale, which creates a natural-language policy concern under the language/locale rule.
Intent-Code Divergence
Low
- Confidence
- 95% confidence
- Finding
- The inline documentation says non-JSON input is treated as plain-text material such as '直接粘贴的合同全文', which contradicts the rest of the file's stated purpose of checking freight loss claim and carrier deduction detail tables with headers. The implementation does indeed pass arbitrary non-JSON text through as `{ text: stripped }`, so the comment broadens the intended material type beyond the declared table-focused scope.
Static analysis
No suspicious patterns detected.