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
合同履约成本与收入配比核对（免费版）
Security checks for vulnerabilities and agentic risk
Overview
This skill is a local Chinese accounting-table checker that reads a user-supplied file and runs bundled Node.js logic without network, persistence, or hidden privilege behavior.
Install only if you are comfortable using a Chinese-language local checker for accounting-table consistency. It processes pasted or file-provided table text locally, but it is not a substitute for accounting judgment, audit work, or verification of contracts, invoices, and receipts.
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
- Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
- 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
Natural-Language Policy Violations
Medium
- Confidence
- 90% confidence
- Finding
- The skill’s primary display name, summary, tags, and descriptions are all presented in Chinese, and the trigger phrases are specified only in Chinese. Although an English description exists on L13, the file does not state that users may choose their preferred language or that responses can be provided in another locale, which can violate a language/locale policy requiring user opt-in.
Natural-Language Policy Violations
Medium
- Confidence
- 97% confidence
- Finding
- The file’s natural-language documentation and user-facing guidance are entirely in Chinese, including usage description, warnings, and returned advice text. This imposes a specific language/locale by default with no indication that users can choose another language, which matches the policy’s language/locale violation criterion.
Natural-Language Policy Violations
Medium
- Confidence
- 90% confidence
- Finding
- The returned advice string is hardcoded in Chinese, and similar user-facing messages throughout the file are likewise Chinese-only. Because the skill does not provide any mechanism for language selection or user opt-in, it may violate organizational language/locale policy.
Natural-Language Policy Violations
Medium
- Confidence
- 94% confidence
- Finding
- All user-facing descriptions, help text, errors, and status messages in this file are written exclusively in Chinese, with no indication that other languages are supported or that Chinese is an intentional, documented locale restriction. This creates a natural-language policy concern because the skill imposes a specific language on users without opt-in.
Natural-Language Policy Violations
Low
- Confidence
- 90% confidence
- Finding
- The JSON sample contains only Chinese-language field labels and content, which implies a fixed language/locale with no indication of user opt-in or alternate language support. Under the stated policy, hard-coding a specific language can be a natural-language policy violation when no choice or justification is provided.
Static analysis
No suspicious patterns detected.