Back to skill

Security audit

通用工程师 开发规范与代码质量

Security checks for vulnerabilities and agentic risk

Overview

This is a Weline engineering standards skill that gives process, validation, and collaboration rules without hidden execution, persistence, or unrelated data access.

Before installing, users should understand that this skill will steer agents toward Weline-specific engineering process, documentation, validation, and internal Chinese collaboration/reporting conventions. It does not add executable code or hidden access, but it may be too opinionated for projects that do not use Weline's agent roles or reporting workflow.

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
  • 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
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (1)

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

The problem report format is entirely specified in Chinese, and the surrounding instructions require agents to use that exact format when reporting issues. This imposes a language choice without any stated user opt-in, alternative locale, or documented region-specific justification.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.