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
部门费用预算执行核对（免费版）
Security checks for vulnerabilities and agentic risk
Overview
This is a local budget-table checking skill with no evidence of network use, persistence, credential access, or hidden behavior.
Review the Chinese-only interface and the free-version scope before installing. The code processes budget table text locally, but the input may contain sensitive financial data, so users should still follow their organization’s data-handling rules.
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
- 98% confidence
- Finding
The file’s user-facing comments, messages, advice, notes, and disclaimers are written entirely in Chinese, indicating the skill is designed to communicate in a fixed language. There is no visible option for the user to choose a language or locale, which matches the policy concern for forced language without opt-in.
- Content
Natural-Language Policy Violations
Medium
- Category
- Not specified by scanner
- Confidence
- 95% confidence
- Finding
The user-facing description, usage text, prompts, and outputs are entirely in Chinese, and the file does not indicate any option for users to choose another language or locale. Under the policy, a skill that imposes a specific language without user opt-in is a natural-language policy violation.
- Content
Intent-Code Divergence
Low
- Category
- Not specified by scanner
- Confidence
- 94% confidence
- Finding
The comment states that non-JSON input is handled as '直接粘贴的合同全文', which describes contract text rather than a department budget execution table. The actual skill is consistently framed elsewhere as checking a 部门费用预算执行表, so this inline documentation contradicts the intended input domain even though the code itself just treats the content as generic text.
- Content