ClawHub
Back to skill

Security audit

Backtest Analyzer

Security checks across malware telemetry and agentic risk

Overview

This is a local backtest CSV analyzer with some under-documented optional analyses, but no evidence of network access, credential use, hidden persistence, or destructive behavior.

Install only if you are comfortable giving the skill access to the specific trading CSVs and optional benchmark files you choose. Use --output only for report paths where writing a JSON file is intended, and review results as financial analysis rather than trading advice.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • 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
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (2)

Lp3

Medium
Category
MCP Least Privilege
Confidence
82% confidence
Finding
The skill advertises local CSV analysis and JSON export, but the manifest does not explicitly declare the file access it relies on. Undeclared read/write capabilities reduce transparency and can lead users or hosting platforms to grant broader access than expected, especially because output writing is supported. In a local-analysis skill, filesystem access is contextually expected, but it still should be declared clearly.

Tp4

High
Category
MCP Tool Poisoning
Confidence
94% confidence
Finding
The static finding indicates the skill performs materially more analysis than its declared purpose, including attribution, benchmark comparison, and additional metrics not disclosed in the description. This kind of description-behavior mismatch is dangerous because users may invoke the skill with a narrower trust assumption while the implementation processes more data dimensions and may infer extra information from trading records. In a financial-analysis context, undisclosed analysis breadth increases privacy, integrity, and trust risks.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.