Ae1
High
- Category
- analysis-evasion
- Content
node scripts/run.mjs --sample # 先看样例
- Confidence
- 100% confidence
- Finding
- Referenced artifact was not completely inspected
Security audit
污水处理费与水质数据核对（免费版）
Security checks for vulnerabilities and agentic risk
Overview
This skill is a local wastewater-fee spreadsheet checker with disclosed local execution and no evidence of network use, persistence, credential access, or hidden behavior.
Install this only if you are comfortable running a local Node-based checker on wastewater fee settlement data. The artifact appears to keep data local, but the table may contain business/financial information, so provide only files you intend the agent and local script to read. Treat the output as arithmetic and consistency checking, not legal, environmental-compliance, audit, or payment authorization 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 Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
- 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
- Content
node scripts/run.mjs --sample # 先看样例
- Confidence
- 100% confidence
- Finding
- Referenced artifact was not completely inspected
Ae1
High
- Category
- analysis-evasion
- Content
node scripts/run.mjs --sample # 先看样例
- Confidence
- 100% confidence
- Finding
- Referenced artifact was not completely inspected
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.
Natural-Language Policy Violations
Medium
- Confidence
- 96% confidence
- Finding
- The file’s primary natural-language description is explicitly written as a Chinese-only engine description, and user-facing strings throughout the skill are exclusively in Chinese. There is no indication that the user can choose another language or that the language restriction is a documented regional requirement, which creates a locale-policy concern.
Natural-Language Policy Violations
Low
- Confidence
- 90% confidence
- Finding
- The user-facing instructions, usage guidance, and operational description are presented only in Chinese in the main markdown content. While there is a short English description in metadata, the skill does not offer language selection or explain that it is intentionally limited to Chinese-speaking users or a China-specific workflow.
Natural-Language Policy Violations
Low
- Confidence
- 93% confidence
- Finding
- This file contains all natural-language documentation, usage text, and runtime messages in Chinese only. Under the policy, forcing a specific language without user opt-in can be a natural-language policy violation unless the locale constraint is explicitly justified; no such opt-in or justification appears here.
Static analysis
No suspicious patterns detected.