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
房产税与城镇土地使用税申报核对（免费版）
Security checks for vulnerabilities and agentic risk
Overview
This skill is a local-only Chinese property and land-use tax worksheet checker with no evidence of network use, persistence, credential access, or hidden behavior.
Install only if you are comfortable running a local Node script over Chinese property tax and urban land-use tax worksheet data. The skill does not appear to send data out, but it is not tax advice and explicitly does not validate local policy choices such as deduction ratios, land grade rates, exemptions, or whether source accounting values are correct.
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 (6)
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
- 95% confidence
- Finding
The skill body is entirely written in Chinese and the usage instructions, warnings, and operational details are only presented in Chinese, while only a brief English summary is provided in metadata. This creates a language-policy concern because the skill effectively requires Chinese comprehension without an explicit opt-in or a clearly documented region/language limitation.
- Content
Natural-Language Policy Violations
Medium
- Category
- Not specified by scanner
- Confidence
- 95% confidence
- Finding
The file’s natural-language descriptions, user-facing advice, sample input headers, and output messages are all written in Chinese, and there is no indication that the skill supports other languages or that Chinese-only use is an intentional, documented locale constraint. This can violate language/locale policy because it implicitly forces a specific language without user opt-in.
- Content
Natural-Language Policy Violations
Medium
- Category
- Not specified by scanner
- Confidence
- 95% confidence
- Finding
The JSON template contains only Chinese field labels and example content, which implies the skill output is fixed to Chinese. Under the policy, forcing a specific language without user opt-in or a documented regional justification is a natural-language policy violation.
- Content
Intent-Code Divergence
Low
- Category
- Not specified by scanner
- Confidence
- 97% confidence
- Finding
The comment says non-JSON input is treated as plain-text material such as a 'directly pasted full contract'. That contradicts the rest of the file and manifest, which consistently describe the expected material as property-tax and urban land-use tax declaration tables, not contracts.
- Content