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
印花税计税依据核对（免费版）
Security checks for vulnerabilities and agentic risk
Overview
This is a coherent local ledger-checking skill for Chinese stamp-duty tax-base tables, with no evidence of network use, persistence, or hidden data handling.
Install only if you are comfortable running a Chinese-language local tool on stamp-duty ledger data. It does not appear to send data out or persist anything, but users should still review outputs as tax-assistance results rather than legal or tax 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 (5)
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
- 97% confidence
- Finding
The file’s comments, user-facing advice, messages, sample input headers, and disclaimer are entirely in Chinese, and the runtime returns Chinese-only strings such as the insufficiency advice and finding messages. This creates a natural-language locale constraint without any opt-in or explicit justification that the skill is region-specific, which matches the language-policy violation criteria.
- Content
Natural-Language Policy Violations
Medium
- Category
- Not specified by scanner
- Confidence
- 95% confidence
- Finding
The user-facing description, usage, errors, and output strings are entirely in Chinese, and the file does not offer any language/locale selection or state that the skill is intentionally limited to Chinese-speaking users or a China-specific compliance environment. Under the policy, forcing a specific language without opt-in is a natural-language locale violation.
- Content
Intent-Code Divergence
Low
- Category
- Not specified by scanner
- Confidence
- 83% confidence
- Finding
The comment on loadInput states that non-JSON input may be '直接粘贴的合同全文', which implies broader document handling than this skill's stated purpose of checking a stamp-duty tax-base ledger row by row. The surrounding help and runtime messages repeatedly require a 台账/表头-based input, so the comment is misleading relative to actual intended use.
- Content