ClawHub
Back to skill

Security audit

WebClip Save & Summarize Web Pages

Security checks across malware telemetry and agentic risk

Overview

This skill appears to do broader web fetching and local content handling than a simple summarizer clearly discloses.

Review this skill carefully before installing. Use it only if you are comfortable with an agent fetching arbitrary URLs and saving fetched content locally. Avoid giving it sensitive intranet, localhost, or authenticated URLs unless you have verified it blocks private targets and only stores content where you expect.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (2)

Lp3

Medium
Category
MCP Least Privilege
Confidence
89% confidence
Finding
The skill explicitly advertises network fetching of arbitrary web pages but does not declare corresponding permissions. In an agent ecosystem, missing permission declarations undermine least-privilege controls and informed user consent, making outbound requests less visible and easier to misuse for unapproved data access or SSRF-like behavior depending on implementation.

Tp4

High
Category
MCP Tool Poisoning
Confidence
83% confidence
Finding
The documented behavior does not fully match the described purpose: it appears to return raw HTML, save content locally, batch-fetch URLs, and may not actually summarize despite claiming summarization. This mismatch is dangerous because reviewers and users may approve the skill for a narrower research-only purpose while it exercises broader data collection and persistence capabilities than expected.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.