ClawHub
Back to skill

Security audit

博客监控

Security checks across malware telemetry and agentic risk

Overview

This skill does what it advertises: it checks RSS feeds or webpages for blog updates, with expected outbound web requests.

Install it in a virtual environment and only add public or trusted feeds/pages. Avoid monitoring localhost, private-network addresses, internal admin panels, cloud metadata endpoints, or other sensitive URLs unless you intentionally want the agent to request them.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (1)

Missing User Warnings

Medium
Confidence
94% confidence
Finding
The skill performs outbound network requests to arbitrary monitored URLs via RSS parsing and direct HTTP GETs, but the markdown does not warn users that activating it will contact external sites. This can expose user IP/network metadata, trigger access to internal or sensitive endpoints if user-supplied URLs are accepted, and create SSRF-like risk in agent environments with privileged network access.

VirusTotal

66/66 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.