ClawHub

daily-news-collector

Security checks across malware telemetry and agentic risk

Overview

This skill does what it claims: it collects configured news/RSS/web content and writes local report files, with no hidden credential access, persistence, or destructive behavior found.

Before installing, review the configured RSS feeds, URL lists, and output paths. Avoid pointing it at private/internal URLs or pages containing sensitive data, and run scraping at a respectful rate consistent with target site terms and robots.txt.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (3)

Lp3

Medium
Category
MCP Least Privilege
Confidence
94% confidence
Finding
The skill clearly instructs the agent to perform network access and local file writes via Python scripts, but the manifest does not declare corresponding permissions or provide explicit user-facing consent boundaries. This creates a transparency and control gap: a user or platform may invoke a skill that can fetch remote content and write artifacts locally without the expected permission metadata.

Vague Triggers

Medium
Confidence
83% confidence
Finding
The trigger conditions are very broad (e.g. any request resembling collecting news, generating reports, or monitoring media), which can cause the skill to activate in contexts the user did not specifically intend. In a skill with network and file-write behavior, overbroad triggering increases the chance of unintended external requests, scraping activity, and local artifact creation.

Missing User Warnings

Medium
Confidence
95% confidence
Finding
The skill documentation describes scraping websites, reading RSS/API data, and saving daily reports, but it does not prominently disclose to the user that invoking the skill will perform outbound network access and local file writes. This undermines informed consent and can lead to unexpected data transfer or filesystem modifications, especially when users assume the skill is analysis-only.

VirusTotal

34/34 vendors flagged this skill as clean.

View on VirusTotal