Gitlab Mr Review

Security checks across malware telemetry and agentic risk

Overview

This skill clearly reviews a user-provided GitLab merge request and posts a review comment, but users should know it acts through their GitLab CLI account.

Install this only if you are comfortable with the agent using your configured GitLab CLI account to read MR diffs and publish review comments. For shared or sensitive repositories, review the generated comment before allowing it to be posted and prefer least-privilege GitLab credentials.

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
96% confidence
Finding
The skill directs the agent to post a merge request comment to GitLab, which is a remote state-changing action, without requiring explicit user confirmation immediately before the write. In an agent setting, this can cause unintended external modifications, spam, or disclosure of sensitive review content to the MR if the user only intended analysis rather than publication.

VirusTotal

62/62 vendors flagged this skill as clean.

View on VirusTotal