Security audit

Go Lint 配置工具

Security checks for vulnerabilities and agentic risk

Overview

This Go linting skill is mostly ordinary, but its instructions claim broader powers than a lint configuration helper needs.

Review before installing. Use this only for Go golangci-lint configuration and troubleshooting, and confirm any file writes such as .golangci.yml before allowing the agent to save changes or run install/lint commands.

SkillSpector

Vulnerability Patterns

Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
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

Findings (5)

Description-Behavior Mismatch

Medium

Confidence: 91% confidence
Finding: The manifest description mixes Go linting with unrelated project management and team-collaboration claims, which can cause the agent to invoke this skill outside its intended scope. In an agent ecosystem, inaccurate scope metadata is security-relevant because it increases the chance the skill is selected in inappropriate contexts, leading to unnecessary tool use and repository interaction.

Intent-Code Divergence

Medium

Confidence: 89% confidence
Finding: The documentation advertises generic create/query/modify/delete-style capabilities and structured parameter operations that do not match the actual lint-config content. This kind of capability inflation can mislead an agent into treating the skill as broadly authorized to manipulate data or files, increasing the risk of unintended actions when paired with write/exec tools.

Vague Triggers

High

Confidence: 94% confidence
Finding: The manifest's broad, mismatched activation scope can cause the agent to invoke a skill with exec/read/write capabilities for unrelated project-management or collaboration requests. Over-broad routing is dangerous because it expands the attack surface and may trigger filesystem or command execution in contexts where a linting tool should never be used.

Vague Triggers

Medium

Confidence: 87% confidence
Finding: The trigger condition is vague and broad ('code generation, programming assistance, debugging, deployment'), which can cause accidental invocation across many software tasks unrelated to linting. In a skill that can use exec and write, ambiguous activation criteria materially increase the chance of unintended side effects.

Missing User Warnings

Medium

Confidence: 84% confidence
Finding: The skill describes exporting/saving results and includes write capability, but it does not clearly warn that repository files may be modified or require explicit user approval before writing. That omission can lead to silent or unexpected changes to tracked configuration files, which is especially risky in automated agent workflows.

Static analysis

No suspicious patterns detected.