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
运单回单与代收货款核对（免费版）
Security checks for vulnerabilities and agentic risk
Overview
This skill is a local Chinese-language reconciliation checker that reads user-provided waybill/POD/COD table data and does not show network, persistence, credential, or hidden mutation behavior.
Install only if you are comfortable with a Chinese-language local checker for business reconciliation tables. It processes the input file you provide and appears not to send data out, but its conclusions are limited to table arithmetic/consistency checks and should not be treated as legal, accounting, or contract advice.
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
- 94% confidence
- Finding
The file’s natural-language instructions, comments, user-facing messages, and sample content are written entirely in Chinese, and the runtime responses returned to users are also hard-coded in Chinese. There is no indication that the user can choose another language or that the skill is explicitly restricted to a China-specific deployment context.
- Content
Natural-Language Policy Violations
Low
- Category
- Not specified by scanner
- Confidence
- 76% confidence
- Finding
The main user-facing instructions and operational guidance in SKILL.md are entirely in Chinese, while only a brief English description is provided in metadata. This can amount to a language/locale constraint for users who cannot read Chinese, without explicitly offering a language choice or documenting the restriction as a justified locale-specific limitation.
- Content
Natural-Language Policy Violations
Low
- Category
- Not specified by scanner
- Confidence
- 90% confidence
- Finding
The script’s help text, status messages, and usage guidance are entirely in Chinese, including the main description and all runtime output. This imposes a specific language on users without any visible option to select another language, which matches the locale-policy concern for natural-language content.
- Content
Intent-Code Divergence
Low
- Category
- Not specified by scanner
- Confidence
- 84% 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', implying the runner is intended to accept full contract text. That contradicts the rest of the file and manifest, which consistently state the skill is for reconciling a 运单回单与代收货款核对表 with table headers, not arbitrary contract documents.
- Content
Natural-Language Policy Violations
Low
- Category
- Not specified by scanner
- Confidence
- 92% confidence
- Finding
The JSON value on L2 is entirely in Chinese, including headers and business labels, and there is no accompanying natural-language indication that this file is region-specific or that users can choose another language. Under the policy rule for language/locale constraints, fixed-language content without opt-in or documented justification can be a policy violation.
- Content