ClawHub
Back to skill

Security audit

GST + UPI Reconciliation Copilot (India)

Security checks across malware telemetry and agentic risk

Overview

This skill locally reconciles user-provided GST and UPI CSV files and writes clearly described report files, with no evidence of hidden network access or unrelated behavior.

Install only if you intend to process GST and UPI exports. Run it on trusted CSVs, write reports to a private folder, avoid shared or synced locations unless appropriate, and review the generated unmatched reports before relying on them for accounting or audit decisions.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • 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
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (2)

Lp3

Medium
Category
MCP Least Privilege
Confidence
90% confidence
Finding
The skill instructs the agent to read input CSVs and write multiple output files, but no permissions are declared to make those capabilities explicit or constrain their use. This creates a transparency and governance gap: an agent may access local business records and persist audit artifacts to disk without clear authorization boundaries, which is risky because the data involved is sensitive financial and tax information.

Missing User Warnings

Low
Confidence
85% confidence
Finding
The skill directs creation of reconciled and unmatched report files containing GST invoices, UPI transactions, and summary data, but does not warn the user that sensitive audit and payment data will be written to disk. In this context, silent persistence can expose financial records through shared machines, synced folders, backups, or mismanaged output locations, even if the core reconciliation logic is legitimate.

VirusTotal

66/66 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.