Permission Footprint Reviewer

• Outcome: Pass
• Latest audit: May 29, 2026, 8:24 PM
• Version:
  1.0.0

Overview

This skill is a local permission-review helper that processes user-provided files and writes optional reports, with no evidence of network access, persistence, credential use, or hidden system changes.

Safe to install for local permission-review workflows. Treat any files you provide as input to a local analyzer, prefer redacted inputs for sensitive material, and choose output paths deliberately because the helper can write a report file when asked.

SkillSpector

By NVIDIA

Vulnerability Patterns

• MCP Least Privilege: Underdeclared Capability, Wildcard Permission, Missing Permission Declaration
• MCP Tool Poisoning: Hidden Instructions, Unicode Deception, Parameter Description Injection
• 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

Findings (2)

Lp3

Medium

• Category: MCP Least Privilege
• Confidence: 90% confidence
• Finding: The skill advertises and documents execution via `python3` and references reading local resources and writing output, but it does not declare corresponding permissions. This creates a transparency and policy-enforcement gap: a reviewer or runtime may assume the skill is lower risk than it really is, enabling unexpected file access or shell execution in environments that rely on declared permissions.

Tp4

High

• Category: MCP Tool Poisoning
• Confidence: 85% confidence
• Finding: The documented purpose is narrow—permission-footprint review—but the described/observed behavior indicates broader scanning and report-generation capabilities across files and directories, including regex-based content inspection. That mismatch is dangerous because it can justify broader access than users expect, increase data exposure during analysis, and conceal a general-purpose scanner behind a specialized security label.

VirusTotal

66/66 vendors flagged this skill as clean.