ClawHub
Back to skill

Security audit

Industry News Summary

Security checks across malware telemetry and agentic risk

Overview

This skill coherently fetches public AI news and writes a local dated summary, with no evidence of credential access, exfiltration, or destructive behavior.

Before installing, be aware that running the skill may leave daily AI news summaries in a local memory/ folder. This is ordinary local caching of public news content, but delete those files if your workspace has strict retention or audit requirements.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • 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
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (2)

Tp4

High
Category
MCP Tool Poisoning
Confidence
91% confidence
Finding
The skill’s declared purpose is to fetch and summarize public AI news, but the implementation notes also introduce persistent local storage in memory/ without surfacing that behavior in the main description or commands. Hidden or under-disclosed persistence changes the trust and privacy model of the skill and can cause users or operators to unknowingly retain data on disk.

Missing User Warnings

Low
Confidence
84% confidence
Finding
Describing local caching to disk without a clear warning reduces transparency around data retention and may lead users to persist content unintentionally. Even if the news data is public, stored summaries can still create audit, retention, or workspace hygiene issues in environments where local persistence is sensitive.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.