ClawHub
Back to skill

Security audit

Trello

Security checks across malware telemetry and agentic risk

Overview

This Trello skill is a straightforward API helper, but users should know its examples can read and change Trello cards when run with their token.

Use this only if you are comfortable giving the agent Trello API access. Keep the API key and token secret, review board/list/card IDs before POST or PUT commands, and revoke the token when it is no longer needed.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • 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
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (1)

Missing User Warnings

Medium
Confidence
94% confidence
Finding
The skill includes write-capable operations such as creating cards, moving cards, commenting, and archiving cards, but it does not clearly warn users that these commands will modify remote Trello data. In an agent context, this increases the risk of unintended state changes to production boards because destructive or persistent actions are presented alongside read operations without explicit confirmation guidance.

VirusTotal

65/65 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.