ClawHub
Back to skill

Security audit

CAI: buy-software-license-agent

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed payment workflow for software licenses that requires explicit confirmation before transfer, though users should treat it as financially sensitive.

Install only if you intend to let an agent prepare CAI wallet payments for software or SaaS purchases. Before approving any transfer, verify the vendor, destination, amount, chain, token, and API key scope; prefer the narrowest CAI_API_KEY permissions available.

A.I.G

Vulnerability Patterns
  • Skill Instruction HijackingAlters the agent's session goals or safety constraints when the skill loads
  • Agent Memory PoisoningWrites attacker-controlled rules into memory that affect later sessions
  • Remote Payload Retrieval and ExecutionFetches external code whose behavior can change after review
  • Embedded Malicious CodeShips malicious scripts inside the skill and executes them locally
  • Unauthorized Access and Privilege EscalationObtains permissions beyond the task's legitimate needs

SkillSpector

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 (1)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The trigger examples are very broad natural-language payment requests such as 'Buy this software license for me' and 'Renew my subscription — agent pays,' which can cause the skill to be selected in situations where the user has not clearly intended to invoke a payment-capable agent. Because this skill can ultimately initiate custodial or on-chain transfers after confirmation, accidental or context-confused invocation increases the risk of unintended payment workflows and social-engineering abuse.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.