Back to skill

Security audit

Go代码检查配置工具

Security checks for vulnerabilities and agentic risk

Overview

This is a Markdown-only Go linter configuration skill with broad but purpose-aligned read, write, and command-use expectations, and no evidence of hidden execution, persistence, or data theft.

Before installing, treat this as a lightweight instruction skill rather than an enforced tool. Use it only on Go projects you choose, review any proposed file edits or shell commands before allowing them, and do not provide unrelated API keys unless a concrete integration is actually needed.

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 (3)

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

The description includes natural-language wording that the skill 'supports Chinese interaction' as part of its default behavior, but does not offer the user a language or locale choice. Under the language/locale policy rule, forcing or presuming a specific language without explicit opt-in can be a policy violation.

Content

No source excerpt is available for this finding.

Intent-Code Divergence

Medium
Category
Not specified by scanner
Confidence
89% confidence
Finding

The skill claims command execution is restricted to a whitelist and safe sandbox, but the markdown provides no actual enforcement mechanism, policy definition, or implementation. In an agent environment exposing exec, this can create a dangerous trust gap where operators assume shell actions are constrained when they are not, increasing the chance of unsafe command execution against user-controlled paths or inputs.

Content

No source excerpt is available for this finding.

Intent-Code Divergence

Low
Category
Not specified by scanner
Confidence
80% confidence
Finding

The feature list states '通过标准化接口调用外部服务并处理响应', and surrounding sections discuss API keys, 401/429/504 errors, and HTTPS certificate validation as if the skill actually integrates with remote services. In this file, those are unsupported by any implementation, creating a mismatch between documented behavior and the actual artifact provided.

Content

No source excerpt is available for this finding.