blog-polish-enus-images

• Outcome: Review
• Latest audit: May 29, 2026 at 9:27 PM UTC
• Version:
  1.0.1

Overview

The skill is a code-review helper, but its bundled script defaults to broad unsandboxed review execution and can automatically involve other reviewer tools.

Install only if you trust this maintainer workflow with your repository. Prefer running the helper with `--no-yolo` or `AUTOREVIEW_YOLO=0`, disable automatic fallback reviewers if your diff is private, and review any auto-run test/static-check behavior before use.

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

Low

• Confidence: 80% confidence
• Finding: The skill reads from and writes to local filesystem locations automatically, but the user-facing instructions do not clearly warn that local data will be modified and persisted. In an agent setting, silent file creation/overwrite behavior can surprise users, cause unintended data exposure through later workflows, or alter local content without informed consent.

VirusTotal

66/66 vendors flagged this skill as clean.