ClawHub

HackerNews Extract

Security checks across malware telemetry and agentic risk

Overview

This skill appears safe for its stated purpose: it fetches a Hacker News post and linked article, then saves the result as Markdown.

Install only where outbound web access and uv dependency downloads are acceptable. When used, it may contact Hacker News/Algolia and the article’s original website, create files under the requested output path, and upload the generated Markdown file back to the chat workflow.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • 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 clearly instructs the agent to execute a Python script that reads input, writes output files, and fetches remote content from Hacker News and linked third-party sites, yet the skill metadata does not declare corresponding permissions. This creates a transparency and policy-enforcement gap: agents or review systems may underestimate the skill's access to the filesystem and network, increasing the risk of unintended data exposure, unsafe fetching, or execution in overly permissive contexts.

Missing User Warnings

Low
Confidence
84% confidence
Finding
The description explains functionality but does not clearly warn that the skill retrieves third-party web pages and Hacker News content over the network. Without an explicit warning, users may invoke it without realizing it contacts external services and processes untrusted remote content, which can have privacy, compliance, and safety implications in restricted environments.

VirusTotal

65/65 vendors flagged this skill as clean.

View on VirusTotal