Skill Listing Polisher

• Outcome: Review
• Latest audit: May 29, 2026 at 9:23 PM UTC
• Version:
  0.1.0

Overview

The skill is a disclosed code-review helper, but its default full-access nested reviewer and broad repository diff sharing deserve user review before installation.

Install only if you are comfortable letting the helper read repository diffs, including untracked files, and potentially send those diffs to configured reviewer CLIs. Prefer running it with --no-yolo, disable fallback reviewers when not needed, and avoid using it on repositories containing secrets or private code you do not want shared with external AI tools.

SkillSpector

By NVIDIA

Vulnerability Patterns

• MCP Least Privilege: Underdeclared Capability, Wildcard Permission, Missing Permission Declaration
• 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

Findings (1)

Lp3

Medium

• Category: MCP Least Privilege
• Confidence: 93% confidence
• Finding: The skill instructs the user to run a bundled shell script against a target path, which implies file-read capability, but no corresponding permissions are declared. This mismatch can bypass user expectations and platform review signals, and in this specific context is more suspicious because the skill explicitly aims to make a package look 'less suspicious' and 'normal in review,' which can facilitate concealment of risky contents.

VirusTotal

66/66 vendors flagged this skill as clean.