ClawHub

网页内容提取小助手

Security checks across malware telemetry and agentic risk

Overview

This is a straightforward webpage extraction skill whose network access matches its stated purpose, with some privacy and dependency hygiene cautions.

Install only if you are comfortable with a skill making outbound requests to URLs you provide. Avoid using it on localhost, private-network services, internal dashboards, or URLs containing secrets, and prefer running it in an isolated Python environment with pinned dependency versions.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • 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 (5)

Vague Triggers

Medium
Confidence
84% confidence
Finding
The README shows a natural-language trigger that can cause the skill to fetch and extract content from an arbitrary user-provided URL without documenting scope restrictions, trust boundaries, or approval requirements. In an agent setting with network permission, this broad phrasing can encourage unsafe use such as fetching internal resources, attacker-controlled URLs, or sensitive endpoints, increasing SSRF-like and data-handling risk.

Missing User Warnings

Medium
Confidence
88% confidence
Finding
The README advertises extraction from arbitrary webpage URLs and structured output but does not clearly warn that supplying a URL will trigger outbound network requests and ingestion of remote content. In an agent environment, this omission can mislead users or integrators about privacy, logging, and exposure risks when user-supplied URLs are fetched and their contents processed.

Unpinned Dependencies

Low
Category
Supply Chain
Content
requests>=2.28.0
beautifulsoup4>=4.11.0
Confidence
97% confidence
Finding
requests>=2.28.0

Unpinned Dependencies

Low
Category
Supply Chain
Content
requests>=2.28.0
beautifulsoup4>=4.11.0
Confidence
97% confidence
Finding
beautifulsoup4>=4.11.0

Known Vulnerable Dependency: requests — 10 advisory(ies): CVE-2014-1830 (Exposure of Sensitive Information to an Unauthorized Actor in Requests); CVE-2024-47081 (Requests vulnerable to .netrc credentials leak via malicious URLs); CVE-2024-35195 (Requests `Session` object does not verify requests after making first request wi) +7 more

High
Category
Supply Chain
Confidence
92% confidence
Finding
requests

VirusTotal

59/59 vendors flagged this skill as clean.

View on VirusTotal