ClawHub
Back to skill

Security audit

finance-analyzer

Security checks across malware telemetry and agentic risk

Overview

This skill locally analyzes user-provided financial spreadsheets and does not show hidden data sharing, credential use, or destructive behavior.

Install only in a Python environment you trust, review or pin pandas/openpyxl if dependency control matters, and run the analyzer only on financial files you intend to process locally. Use the optional output path carefully because it can write or overwrite a JSON file at the path the agent chooses.

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
92% confidence
Finding
The skill instructs the agent to install packages and run a local script with an optional `--output <output.json>` argument, which implies file-write capability, but no permissions are declared. Undeclared write behavior is risky because users and policy systems cannot accurately constrain side effects, and a crafted workflow could cause unexpected files to be created or overwritten during analysis.

Vague Triggers

Medium
Confidence
83% confidence
Finding
The trigger description activates on broad phrases like 'analyze this financial report' or 'any task involving reading and interpreting financial spreadsheets,' which can cause the skill to run in situations beyond its narrowly intended scope. Over-broad activation increases the chance that the agent will process untrusted spreadsheets, install dependencies, or execute the bundled script when simpler or safer handling would be more appropriate.

VirusTotal

56/56 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.