ClawHub
Back to skill

Security audit

Finance Report Tool Free

Security checks across malware telemetry and agentic risk

Overview

This appears to be a local finance-report skill with some overly broad routing language but no evidence of hidden data theft, destructive behavior, or persistence.

Install only if you are comfortable with an agent reading local financial files, installing Python dependencies, running local Python commands, and writing HTML reports. Prefer giving it explicit finance-report tasks and an explicit output directory, because its trigger wording is broader than necessary.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (3)

Vague Triggers

Medium
Confidence
91% confidence
Finding
The description includes broad 'Use when' phrasing around generic data analysis, reporting, statistics, and visualization tasks, which can cause the agent to invoke this skill outside its narrow finance-report purpose. Because the skill advertises exec/write capabilities, over-broad activation increases the chance of unnecessary local command execution and file creation in contexts the user did not specifically request.

Vague Triggers

Medium
Confidence
95% confidence
Finding
The skill declares an extremely broad keyword coverage list, including fragmented and generic terms that could match many unrelated prompts. In an agent environment, this can hijack routing and cause a high-privilege skill with read/write/exec access to be selected for tasks beyond its intended scope.

Missing User Warnings

Medium
Confidence
93% confidence
Finding
The markdown does not clearly warn users that the skill writes HTML reports to disk and may execute local Python commands. Without explicit disclosure, users and orchestrators may treat it as a passive analysis skill, increasing the risk of unexpected file-system changes or command execution when the skill is auto-invoked.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.