Ae1
High
- Category
- analysis-evasion
- Content
node scripts/run.mjs --sample # 先看样例（样例本身就是一张自洽的表）
- Confidence
- 100% confidence
- Finding
- Referenced artifact was not completely inspected
Security audit
保险佣金与手续费结算核对（免费版）
Security checks for vulnerabilities and agentic risk
Overview
This skill is a local insurance commission spreadsheet checker that reads user-provided input and does not show evidence of network access, persistence, credential use, or hidden high-impact actions.
Use this only with insurance commission settlement tables you are comfortable processing locally. It appears designed to run offline, but users should note that the interface and examples are Chinese-language focused and that the free version intentionally omits some advanced checks such as difference attribution.
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 (8)
Ae1
High
- Category
- analysis-evasion
- Content
node scripts/run.mjs --sample # 先看样例（样例本身就是一张自洽的表）
- 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（样例本身就是一张自洽的表）
- Confidence
- 100% confidence
- Finding
- Referenced artifact was not completely inspected
Natural-Language Policy Violations
Medium
- Confidence
- 94% confidence
- Finding
- The file’s natural-language instructions and descriptions are entirely in Chinese, including operational guidance and warnings, with no indication that users can choose another language or locale. Under the policy, forcing a single language without opt-in is a natural-language policy violation unless the locale restriction is clearly documented and justified.
Natural-Language Policy Violations
Medium
- Confidence
- 95% confidence
- Finding
- The file's user-facing documentation, usage text, prompts, and status/output messages are entirely in Chinese, with no indication that users can select another language or locale. Under the stated policy, forcing a specific language without user opt-in is a natural-language policy violation.
Intent-Code Divergence
Low
- Confidence
- 97% confidence
- Finding
- The inline result disclaimer claims the tool checks "合计行、重复结算、档位与差异归因". However, the implemented free checks only cover the 6 listed checks, and the file-level comments explicitly say difference attribution is withheld for the paid version. This is an active documentation contradiction about what the current code does.
Intent-Code Divergence
Low
- Confidence
- 94% confidence
- Finding
- The comment says non-JSON input is treated as plain-text material such as '直接粘贴的合同全文', which broadens the documented intent to arbitrary contract text. However, the surrounding code, help text, and manifest consistently position the skill as operating on 保险佣金与手续费结算明细表 with table headers, so this inline documentation contradicts the stated narrow purpose.
Natural-Language Policy Violations
Low
- Confidence
- 92% confidence
- Finding
- The JSON sample content is entirely in Chinese, including headers and notes, with no indication that the skill supports other languages or that Chinese output is optional. For a general-purpose template file, this can violate language/locale policy by implicitly forcing a specific language without user opt-in.
Static analysis
No suspicious patterns detected.