ClawHub
Back to skill

Security audit

Simple RSS news feed

Security checks across malware telemetry and agentic risk

Overview

This appears to be a straightforward RSS news-headline skill, with network fetching disclosed and aligned to its purpose.

Install only if you are comfortable with the agent making outbound requests to public news RSS sources when you ask for current headlines. The publisher should ideally make the network requirement explicit in metadata and narrow invocation wording, but the available evidence does not show malicious or materially unsafe behavior.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • 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
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (2)

Lp3

Medium
Category
MCP Least Privilege
Confidence
95% confidence
Finding
The skill explicitly states it uses HTTP to fetch external RSS feeds, which is a network capability, but the metadata only declares a Python runtime requirement and no corresponding permission or capability declaration. Undeclared network access weakens security review and policy enforcement because an agent or platform may invoke a skill with broader behavior than its manifest suggests.

Vague Triggers

Medium
Confidence
88% confidence
Finding
The 'When to Use' section uses very broad phrases like 'latest news', 'current events', and 'what's happening in the world', which could cause the skill to activate in many ordinary conversations where the user did not intend tool use. Over-broad activation guidance increases the chance of unnecessary external network requests and unintended disclosure of user interests or context to third-party news sources.

VirusTotal

66/66 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.