ClawHub
Back to skill

Security audit

review-github-pr

Security checks across malware telemetry and agentic risk

Overview

This skill is a disclosed GitHub PR review helper that uses git, gh, local checks, and confirmed review posting in ways that match its purpose.

Install this only if you are comfortable letting the agent use git and gh against repositories you review, read PR files and diffs, run repository validation commands, and post GitHub reviews after you confirm. Before confirming any post, review the draft carefully, especially in public or production repositories.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • 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)

Lp3

Medium
Category
MCP Least Privilege
Confidence
93% confidence
Finding
The skill clearly performs shell and network operations (`gh`, `git`, cloning repos, posting reviews) but does not declare permissions for those capabilities. That creates a transparency and policy-enforcement gap: a host may allow the skill to run without surfacing the true blast radius, enabling unexpected external access or command execution in the user's environment.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.