ClawHub
Back to skill

Security audit

FlowUs CLI

Security checks for vulnerabilities and agentic risk

Overview

This skill gives agents cautious instructions for using the FlowUs CLI with authentication, installation, and write actions gated by explicit user control.

Before installing, confirm you trust the FlowUs CLI distribution and only approve install, login, uploads, or page/database writes when the target workspace and expected changes are clear. Use a proper secret channel for credentials rather than pasting tokens into chat.

SkillSpector

Vulnerability Patterns
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • 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 (2)

Autonomous Decision Making

Medium
Category
Excessive Agency
Content
Use the FlowUs CLI (`flowus`) for FlowUs V2 API work: pages, blocks,
databases, search, Markdown content, and files.

The CLI source repository may be private. Do not ask the user to clone source
code before using the CLI. Install or update the released binary from the
official FlowUs CDN only after the user explicitly approves it.
Confidence
80% confidence
Finding
Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.

Autonomous Decision Making

Medium
Category
Excessive Agency
Content
This is CLI resolution behavior, not authorization to expose a credential. Do
not pass `--token` in agent commands, logs, or shared shells: it can leak via
process listings or shell history. Do not ask users to paste bearer tokens into
chat. Use preconfigured `FLOWUS_TOKEN`, saved credentials, or an approved secret
channel; redact any credential that appears in command output.
Confidence
80% confidence
Finding
Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.

Static analysis

No suspicious patterns detected.