ClawHub
Back to skill

Security audit

Dropbox

Security checks for vulnerabilities and agentic risk

Overview

This appears to be a Dropbox management skill with sensitive but expected account access, and the main issue is overly broad activation wording rather than evidence of abuse.

Install only if you want an agent to manage Dropbox data for you. Use explicit prompts for uploads, moves, edits, shares, or deletes, and require confirmation before destructive or bulk operations. The publisher should narrow the activation wording so casual Dropbox mentions do not route into this skill.

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
92% confidence
Finding
The skill description instructs the agent to use this skill for ANY Dropbox-related request, which is an overly broad routing rule. Because this skill includes read, write, and destructive actions, automatic selection based only on the word 'Dropbox' can bypass more nuanced task routing and increase the chance of unintended state-changing operations being invoked in contexts where a narrower or safer flow should be used.

Static analysis

No suspicious patterns detected.