ClawHub
Back to skill

Security audit

Golang Error Handling

Security checks across malware telemetry and agentic risk

Overview

This is a Go error-handling guidance skill with broad but disclosed coding and audit permissions that fit its stated purpose.

Install this for Go projects where you want an agent to write, review, or audit error handling. It can modify repository files, run Go/git-related commands, and launch audit sub-agents, so use it only in workspaces where that level of code access is acceptable.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • 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
Findings (2)

Vague Triggers

Low
Confidence
89% confidence
Finding
The description says to apply the skill whenever creating, wrapping, inspecting, or logging errors in Go code, which is a very wide scope and does not define exclusions or narrower trigger phrases. For a manifest/markdown-scoped trigger review, this can overlap with many ordinary Go coding requests and may cause unintended activation.

Autonomous Decision Making

Medium
Category
Excessive Agency
Content
// ✗ Bad — only checking in some branches
result, err := doSomething()
fmt.Println(result) // using result without checking err

// ✓ Good — always check before using other return values
data, err := os.ReadFile("config.yaml")
Confidence
75% confidence
Finding
without checking

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.