Back to skill

Security audit

Cn Web Clipper

Security checks across malware telemetry and agentic risk

Overview

This is a straightforward web clipping skill that fetches a user-provided webpage and saves extracted text locally, with no evidence of hidden execution, exfiltration, or destructive behavior.

Install only if you are comfortable with the skill fetching URLs you provide and saving extracted webpage text to your filesystem. Prefer a dedicated output folder, avoid clipping sensitive internal URLs unless intended, and note that repeated clips with the same title and date may overwrite the same Markdown filename.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (2)

Lp3

Medium
Category
MCP Least Privilege
Confidence
92% confidence
Finding
The skill documentation describes behavior that fetches remote webpages and saves extracted content to local Markdown files, which implies network and file-write capabilities, yet no permissions are declared. This creates a transparency and review gap: users or platforms may not realize the skill can access external URLs and write data locally, increasing the risk of unintended data writes, misuse of sensitive local paths, or unsafe execution in restricted environments.

Missing User Warnings

Low
Confidence
88% confidence
Finding
The usage text says the tool extracts webpage content and saves it as Markdown, but it does not clearly warn users that running the skill writes content to the local filesystem. Lack of an explicit write warning can lead to surprise persistence, accidental overwrites, or unsafe use in environments where local writes should be tightly controlled.

VirusTotal

65/65 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.