ClawHub

Pane

Security checks across malware telemetry and agentic risk

Overview

This is a clearly disclosed Pane finance-data integration; it handles very sensitive data, but the artifacts do not show hidden, unrelated, or malicious behavior.

Install only if you trust Pane and the mcporter dependency with your financial data. Keep PANE_API_KEY in an environment variable, avoid putting secrets or unnecessary personal details in annotations, use Pane privacy scopes, and periodically review or delete saved annotations.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • 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
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (2)

Missing User Warnings

Medium
Confidence
89% confidence
Finding
The skill clearly enables access to highly sensitive personal financial data including accounts, transactions, liabilities, investments, and crypto, but it does not present a prominent privacy warning or consent reminder near the top-level description and setup flow. In an agent context, users may invoke or install the skill without appreciating the scope of data exposure, increasing the risk of over-collection, accidental disclosure in conversation history, or use beyond the user's expectations.

Missing User Warnings

Medium
Confidence
92% confidence
Finding
The skill offers persistent server-side annotations tied to profile, merchants, accounts, and transactions, but the warning about persistence and future visibility is relatively understated compared with the feature description and examples. This creates a real risk that users or agents will store sensitive personal inferences or contextual notes that persist across sessions and later appear in tool results, causing unintended retention and disclosure of financial context.

VirusTotal

65/65 vendors flagged this skill as clean.

View on VirusTotal