ClawHub
Back to skill

Security audit

golang-structs-interfaces

Security checks for vulnerabilities and agentic risk

Overview

This is a normal Go coding-guidance skill with no install script, persistence, or hidden data-handling behavior.

Install this if you want Go type-design guidance. Because the skill can edit Go files and run Go, golangci-lint, and git commands, review proposed file changes and git operations before accepting them.

A.I.G

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

SkillSpector

Vulnerability Patterns
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • 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 (1)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
89% confidence
Finding

The description says to use this skill for a wide range of situations such as 'when designing Go types' and 'when the user asks about' multiple general concepts, but it does not define clear boundaries or exclusion conditions. In a manifest file, this kind of broad invocation guidance can cause unintended activation for ordinary Golang discussions that may not specifically need this skill.

Content

No source excerpt is available for this finding.