ClawHub
Back to skill

Security audit

golang-graphql

Security checks across malware telemetry and agentic risk

Overview

This skill is a coherent Go GraphQL development guide with disclosed code-editing and documentation lookup capabilities, and no evidence of hidden or harmful behavior.

Installers should expect this skill to help an agent read and edit Go GraphQL code, run Go-related commands, fetch documentation, and optionally use sub-agents for code review. Review changes before applying them in production, especially generated gqlgen output and handler security settings.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • 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 (2)

Vague Triggers

Medium
Confidence
93% confidence
Finding
The manifest description says to apply the skill when 'building GraphQL servers, designing schemas, writing resolvers, handling subscriptions, or integrating GraphQL with existing Go HTTP services,' which describes a very wide range of routine development activity. It does not provide explicit boundaries, exclusions, or negative examples to clarify when the skill should not activate, increasing the risk of unintended invocation.

Hidden Instructions

High
Category
Prompt Injection
Content
## Type Mapping

<!-- prettier-ignore -->
|GraphQL type|Go type|Notes|
|---|---|---|
|`ID`|`graphql.ID`|string alias|
Confidence
21% confidence
Finding
Hidden instructions were detected in comments or invisible text. These could contain malicious directives. Manual review is recommended.

VirusTotal

63/63 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.