ClawHub
Back to skill

Security audit

gitlab-code-reviewer

Security checks across malware telemetry and agentic risk

Overview

This GitLab review skill is mostly purpose-aligned, but it can post public MR comments without a clear final confirmation and has under-scoped handling of GitLab tokens and temporary review files.

Install only if you are comfortable giving it a dedicated, least-privileged GitLab token. Before running it, verify the MR URL host matches the intended GitLab instance, review the exact comments before allowing them to be posted, and delete the temporary /tmp/mr_comments.json file if it is created.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • 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
91% confidence
Finding
The skill explicitly instructs the agent to post inline comments back to GitLab, but it does not require a clear user confirmation immediately before taking that external write action. This creates a real risk of unintended third-party side effects, especially because review comments are visible to collaborators and may be posted based on an inferred rather than explicitly confirmed user intent.

VirusTotal

62/62 vendors flagged this skill as clean.

View on VirusTotal