ClawHub
Back to skill

Security audit

Gitlab

Security checks across malware telemetry and agentic risk

Overview

This is a legitimate GitLab CLI helper, but it gives an agent broad GitLab write and API power without clear safety guardrails.

Install only if you are comfortable letting the agent use your authenticated GitLab CLI context. Use a least-privilege GitLab token and require explicit approval before merges, approvals, pipeline retries, issue or release creation, CI/CD variable changes, non-GET API calls, or commands against private or production projects.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • 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
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (1)

Missing User Warnings

Medium
Confidence
93% confidence
Finding
The skill includes multiple state-changing GitLab commands such as approving and merging merge requests, retrying pipelines, creating issues and releases, and setting CI/CD variables, but it provides no warning that these actions modify remote resources and may have production impact. In an agent setting, presenting destructive or privileged operations alongside read-only commands without explicit confirmation guidance increases the risk of accidental execution against the wrong repository, branch, or environment.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.