ClawHub
Back to skill

Security audit

Laravel Cloud

Security checks across malware telemetry and agentic risk

Overview

This skill is a disclosed helper for reading Laravel Cloud data through OOMOL, with broad wording that users should notice but no evidence of hidden or malicious behavior.

Install this only if you want an agent to read Laravel Cloud data through an OOMOL-connected account. Check the OOMOL connection and API key scopes, be aware that setup may involve installing the oo CLI, and require explicit confirmation before any future connector action that is labeled write or destructive.

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 (1)

Vague Triggers

Medium
Confidence
92% confidence
Finding
The trigger text is explicitly broad: it directs the agent to use this skill for ANY Laravel Cloud request instead of calling the API directly. That can cause the skill to be invoked in contexts where a narrower or more appropriate tool should be used, increasing the chance of unintended data access, unnecessary external calls, or bypass of finer-grained routing and policy decisions.

VirusTotal

63/63 vendors flagged this skill as clean.

View on VirusTotal