ClawHub
Back to skill

Security audit

Float

Security checks for vulnerabilities and agentic risk

Overview

This is a disclosed Float read-only connector skill that uses OOMOL's oo CLI, with no evidence of hidden, destructive, or persistent behavior.

Install this only if you want an agent to query your connected Float workspace through OOMOL. Be aware that even read-only actions may expose business data such as people, clients, projects, and allocations; for ambiguous Float mentions, ask the agent to clarify before running connector calls.

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
Confidence
89% confidence
Finding
The instruction to use this skill for ANY Float request and instead of calling the API directly is overly broad and can cause the agent to invoke the skill whenever Float is mentioned, even when the user did not intend a connector action. This increases the chance of unintended data access or unnecessary external calls, especially because the skill is positioned as the default path for all Float-related tasks.

Static analysis

No suspicious patterns detected.