ClawHub

Firecom

Security checks across malware telemetry and agentic risk

Overview

This appears to be a real Fire.com integration, but it gives an agent broad access to payment-capable financial workflows without clear read-only limits or confirmation rules.

Install only if you intentionally want an agent to access Fire.com through Membrane. Treat action runs and proxy requests as potentially able to change live financial records or payment instructions; review the exact endpoint, method, amount, counterparty, and payload before approving anything beyond read-only lookups.

SkillSpector

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

Vague Triggers

Medium
Confidence
87% confidence
Finding
The skill description is broad enough that it could be invoked for generic requests involving business finances or records, even when the user did not explicitly intend to use Fire.com. In a financial integration, over-broad triggering is risky because it can route an agent toward live account, transaction, or payment operations without sufficient user confirmation.

Missing User Warnings

Medium
Confidence
93% confidence
Finding
The documentation describes access to a payment-capable financial platform but does not warn that some actions may create, modify, or transmit real financial records or payment instructions. In this context, missing safety framing increases the chance an agent treats powerful operations as routine data access, which could lead to unauthorized or accidental financial impact.

Missing User Warnings

Medium
Confidence
96% confidence
Finding
The proxy request section enables direct API calls with arbitrary methods and bodies, but it omits warnings that these requests can modify live Fire.com resources or initiate sensitive financial operations. Because proxying bypasses the safer abstraction of predefined actions, it expands the chance of destructive or unintended writes if an agent constructs the wrong endpoint or payload.

VirusTotal

65/65 vendors flagged this skill as clean.

View on VirusTotal