ClawHub
Back to skill

Security audit

Allowance

Security checks across malware telemetry and agentic risk

Overview

This is a disclosed purchase-wallet skill that can spend money only through scoped user approval, but users should review its payment and automation behavior carefully before installing.

Install only if you want an agent to complete real purchases for you. Review the Allowance CLI/service trust boundary, use strict spending caps and clear item constraints, and be aware that after phone approval the agent is instructed to submit checkout without asking for another confirmation unless the price, item, or required details change.

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
89% confidence
Finding
The trigger guidance is very broad for a high-risk financial skill: it tells agents to invoke the purchase wallet whenever a user asks to buy, order, book, reserve, pay, or spend money, and additionally says the agent should not ask whether to use CLI or MCP. In a spending context, over-broad activation can cause the agent to route ordinary shopping or travel requests into a transaction-capable workflow without sufficient confirmation, increasing the risk of unintended purchases or premature financial actions.

Missing User Warnings

Medium
Confidence
93% confidence
Finding
The README describes capabilities to request spending approval, receive virtual cards, complete checkout, and report receipts, but it does not prominently warn that the skill can initiate real financial transactions or explain the execution consequences. In the context of a wallet and purchasing skill, missing safety disclosure is dangerous because users and integrators may underestimate that invoking the skill can lead to money being spent, card issuance, and merchant interactions.

Vague Triggers

Medium
Confidence
90% confidence
Finding
The skill advertises an extremely broad trigger surface for actions involving spending money, including generic phrases like buy, pay, or spend money on the user's behalf. In a payment-capable skill, overbroad routing is dangerous because it increases the chance of unintended invocation during ambiguous conversations, which can steer the agent into a purchase workflow and collection of sensitive approval details without sufficiently confirming user intent.

VirusTotal

59/59 vendors flagged this skill as clean.

View on VirusTotal