Branch Protection Auditor

• Outcome: Review
• Latest audit: May 29, 2026 at 9:38 PM UTC
• Version:
  1.0.1

Overview

The skill appears to support repository hardening, but its fix path can directly change GitHub branch protection settings without enough built-in scoping or confirmation.

Install only if you want the agent to help modify repository protection rules. Before using the fix command, confirm the exact owner/repo/branch, review the proposed required status checks and review rules, use a least-privileged GitHub token, and prefer a dry-run or manual application path for production repositories.

SkillSpector

By NVIDIA

Vulnerability Patterns

• Prompt Injection: Instruction Override, Hidden Instructions, Exfiltration Commands
• Data Exfiltration: External Transmission, Env Variable Harvesting, File System Enumeration
• Privilege Escalation: Excessive Permissions, Sudo/Root Execution, Credential Access
• Supply Chain: Unpinned Dependencies, External Script Fetching, Obfuscated Code
• Excessive Agency: Unrestricted Tool Access, Autonomous Decision Making, Scope Creep

Findings (1)

Missing User Warnings

Medium

• Confidence: 93% confidence
• Finding: The `fix` command provides a ready-to-run API call that changes branch protection settings on a repository without any built-in warning, dry-run mode, scope validation, or explicit confirmation step. In an agent skill context, this is dangerous because a user may invoke the skill expecting an audit, while the generated command can directly alter critical repository security controls and potentially cause misconfiguration or unintended operational disruption across repositories.

VirusTotal

65/65 vendors flagged this skill as clean.