ClawHub
Back to skill

Security audit

Stock Screener

Security checks across malware telemetry and agentic risk

Overview

This is a local stock-screening skill that reads user-provided CSV files and optionally writes CSV results, with no evidence of hidden network access, credential use, or destructive behavior.

Install only if you are comfortable giving the skill access to the CSV files you explicitly pass to it. Use non-sensitive copies of financial datasets when possible, choose --output paths carefully to avoid overwriting files, and be aware that several advertised commands may need a bug fix before they work reliably.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • 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
Findings (3)

Lp3

Medium
Category
MCP Least Privilege
Confidence
91% confidence
Finding
The skill documents local file read/write behavior via CSV input and output commands, but does not declare any corresponding permissions. This creates a transparency and policy-enforcement gap: an orchestrator or user may invoke the skill without understanding that it can access and generate local files, increasing the risk of unintended file exposure or overwrite.

Intent-Code Divergence

Medium
Confidence
99% confidence
Finding
The dispatcher invokes every command handler with four arguments, but several handlers are defined with only three parameters, which will raise a TypeError at runtime for commands like rank, score, summary, and correlation. This creates a reliable denial-of-service condition for normal use of the tool, preventing key functionality from running.

Vague Triggers

Medium
Confidence
82% confidence
Finding
The trigger list includes very broad terms such as 'scan', 'screener', and generic screening-related words that may match unrelated user requests. Over-broad invocation can cause the wrong skill to activate, leading to unintended processing of local CSV files or confusion in workflows involving other finance tools.

VirusTotal

60/60 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.