ClawHub

The Fed Agent

Security checks across malware telemetry and agentic risk

Overview

This skill is a disclosed macroeconomic news-analysis helper, with no evidence of hidden access, persistence, credential use, or destructive behavior.

Install only if you want article-based macroeconomic and central-bank policy analysis. Provide public news URLs, avoid internal or private links, and independently verify economic data, scenario probabilities, and trading implications before acting on them.

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 instructs use of `web_fetch` on a user-provided URL, which is a network-capable action, but no permissions or explicit capability declaration are present. This creates a transparency and policy-enforcement gap: users and hosting systems may not realize the skill performs outbound requests, increasing the risk of unexpected data exfiltration, SSRF-like fetching of internal URLs where applicable, or accidental access to sensitive endpoints.

Vague Triggers

Medium
Confidence
84% confidence
Finding
The trigger description is very broad, covering generic news about rates, inflation, economic data, or monetary policy. Overbroad routing can cause the skill to activate on unrelated or adversarial content, unnecessarily exposing it to untrusted URLs and increasing the chance of misuse or prompt-injection attempts through fetched articles.

Missing User Warnings

Low
Confidence
91% confidence
Finding
The skill says it will fetch a user-supplied URL but does not warn the user about external network access or associated risks. Even when the fetched content is only a news article, this omission weakens informed consent and can hide privacy or security implications, especially if users supply unexpected or internal links.

VirusTotal

60/60 vendors flagged this skill as clean.

View on VirusTotal