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
二次供水清洗消毒与水质检测核对（免费版）
Security checks for vulnerabilities and agentic risk
Overview
This is a local, purpose-specific checker for Chinese secondary water supply ledgers, with no evidence of hidden networking, persistence, credential use, or destructive behavior.
Install only if you are comfortable running a local Node script on ledger text you provide. It does not verify real-world certificate authenticity or replace regulatory review, and its built-in guidance is primarily Chinese and specific to secondary water supply records.
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 Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
- 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
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
Lp1
High
- Category
- MCP Least Privilege
- Confidence
- 75% confidence
- Finding
The skill uses 'env' capability that is not listed in its permissions. This may indicate deceptive intent or missing permission declarations.
- Content
Natural-Language Policy Violations
Medium
- Category
- Not specified by scanner
- Confidence
- 91% confidence
- Finding
The file’s natural-language contract and all user-facing guidance are written exclusively in Chinese, indicating the skill is intended to operate in a single language/locale. The policy requires language or locale constraints to be optional, justified, or offered with user opt-in; this file does not present any such choice or explicit justification.
- Content
Intent-Code Divergence
Low
- Category
- Not specified by scanner
- Confidence
- 91% confidence
- Finding
The comment on L075 states that non-JSON input is treated as plain-text material such as '直接粘贴的合同全文', which contradicts the skill's stated purpose and surrounding help text that require a 二次供水清洗消毒与水质检测台账 with headers. This is not just incomplete wording: it actively describes a different document type than the code is intended to process.
- Content
Natural-Language Policy Violations
Low
- Category
- Not specified by scanner
- Confidence
- 89% confidence
- Finding
This JSON template contains user-facing tabular text exclusively in Chinese, but it does not state that the skill is China/Chinese-specific or offer any language choice. Under the natural-language policy rules, forcing a specific language without user opt-in can be a locale-policy issue.
- Content