ClawHub
Back to skill

Security audit

Dida365

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed Dida365 task-management connector that uses OOMOL's oo CLI, with clear confirmation requirements for write and delete actions.

Install this only if you want an agent to operate your connected Dida365 account through OOMOL. Reads may run directly, while creates, updates, moves, completions, and deletes should be reviewed carefully before approval, especially because delete actions can remove task or project data.

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
93% confidence
Finding
The manifest description says to use this skill for "ANY Dida365 request" and "instead of calling the API directly," which is an overly broad routing trigger. This can cause the agent to invoke the skill in situations where narrower or safer handling would be more appropriate, increasing the chance of unintended data access or state-changing operations in a task-management integration that supports create, update, move, complete, and delete actions.

Static analysis

No suspicious patterns detected.