Code Review Engine

• Outcome: Pass
• Latest audit: May 28, 2026 at 1:04 PM UTC
• Version:
  1.0.0

Overview

This is a markdown-only code review skill whose code and PR access is aligned with reviewing code, with optional GitHub commenting that users should explicitly control.

Install if you are comfortable letting the agent read the code, diffs, and PRs you ask it to review. Before using GitHub CLI or scheduled review workflows, confirm the active GitHub account, target repository, and whether the agent is allowed to post PR comments.

SkillSpector

By NVIDIA

Vulnerability Patterns

• Data Exfiltration: External Transmission, Env Variable Harvesting, File System Enumeration
• Trigger Abuse: Overly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
• Prompt Injection: Instruction Override, Hidden Instructions, Exfiltration Commands
• Privilege Escalation: Excessive Permissions, Sudo/Root Execution, Credential Access
• Supply Chain: Unpinned Dependencies, External Script Fetching, Obfuscated Code

Findings (2)

Vague Triggers

Medium

• Confidence: 89% confidence
• Finding: The trigger phrase "review this" is extremely generic and likely to appear in ordinary conversation, pasted code requests, or unrelated context. In an agent environment with automatic or assisted skill routing, this can cause accidental invocation of the skill, leading to unintended code access or follow-on actions such as repo inspection or review workflows.

Missing User Warnings

Medium

• Confidence: 95% confidence
• Finding: The skill explicitly includes a workflow to post PR review comments via `gh pr review ... --comment`, but the user-facing description does not clearly warn that the skill may perform write actions against GitHub. This creates a consent and integrity risk: users may invoke what appears to be a read-only review tool and unintentionally cause public or persistent changes in a repository.

VirusTotal

64/64 vendors flagged this skill as clean.