ClawHub

Sell The News

Security checks across malware telemetry and agentic risk

Overview

This skill is a transparent read-only wrapper for fetching market-news data from Sell The News, with no evidence of hidden persistence, credential use, or destructive behavior.

Install this only if you want your agent to query the Sell The News remote endpoint for market-news and options-related data. Do not pass secrets or sensitive private information as JSON arguments, and only set SELL_THE_NEWS_MCP_ENDPOINT to a server you trust.

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
87% confidence
Finding
The skill instructs use of bundled shell wrappers and `curl`, which implies shell execution and local file access, but it does not declare corresponding permissions. Undeclared capabilities reduce transparency and can bypass policy or user expectations, especially in an agent environment where shell/file access materially increases attack surface.

Vague Triggers

Medium
Confidence
71% confidence
Finding
The trigger description is broad enough to activate for several loosely related requests, including reading/summarizing a site, querying a hosted endpoint directly from shell/OpenClaw, and debugging client compatibility. Over-broad activation can cause unintended invocation of a shell-capable skill, increasing the chance that an agent uses external networked tooling when a safer or more appropriate skill should have been selected.

VirusTotal

65/65 vendors flagged this skill as clean.

View on VirusTotal