ClawHub
Back to skill

Security audit

gqllint

Security checks across malware telemetry and agentic risk

Overview

GQLLint is mostly a local GraphQL scanner, but its license parsing and optional git-hook installer create review-worthy local execution and persistence risks.

Install only if you want a local GraphQL scanner and are comfortable reviewing its scripts first. Use explicit target paths, avoid untrusted license tokens, prefer environment/config secrets over the --license-key flag, and only run hooks install in repositories where persistent commit/push scanning is intended.

SkillSpector

By NVIDIA
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
Confidence
87% confidence
Finding
The skill includes many broad activation phrases such as 'Scan my code for GraphQL issues' and 'Find security issues in my GraphQL setup' without requiring clear GraphQL-specific context, repository scope limits, or user confirmation before scanning. In an agent environment, this can cause over-triggering on vague security-analysis requests and lead to unintended execution over large directories or unrelated codebases, increasing the chance of unnecessary file access and confusing tool selection.

VirusTotal

67/67 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.