Laravel Creem Agent

• Outcome: Review
• Latest audit: May 29, 2026 at 9:29 PM UTC
• Version:
  1.0.5

Overview

This is a coherent local payment-store skill, but it can route broad prompts into sensitive store reads and store-changing actions without a clear confirmation boundary.

Review before installing in production. Use it only if you trust the local Laravel Creem Agent endpoint, restrict who can send OpenClaw commands, and add service-side authentication, audit logging, and confirmation checks for cancellation, checkout creation, store switching, and monitoring actions.

SkillSpector

By NVIDIA

Vulnerability Patterns

• Trigger Abuse: Overly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
• Prompt Injection: Instruction Override, Hidden Instructions, Exfiltration Commands
• Data Exfiltration: External Transmission, Env Variable Harvesting, File System Enumeration
• Privilege Escalation: Excessive Permissions, Sudo/Root Execution, Credential Access
• Supply Chain: Unpinned Dependencies, External Script Fetching, Obfuscated Code

Findings (2)

Vague Triggers

Medium

• Confidence: 89% confidence
• Finding: The skill description includes broad triggers like 'status' and repeated store/payment terms that can overlap with ordinary conversation, increasing the chance the skill activates when the user did not intend to query the payment system. In a payment-management skill, accidental activation can cause unnecessary access to sensitive business data or unintended operational actions.

Vague Triggers

Medium

• Confidence: 91% confidence
• Finding: The supported command examples contain vague phrases such as 'what's going on?', 'check now', and 'monitor' without strong domain qualifiers. This broadens invocation scope and can route unrelated user messages into a skill that can query or modify store state, which is risky in a payments context.

VirusTotal

64/64 vendors flagged this skill as clean.