ClawHub
Back to skill

Security audit

Trello

Security checks across malware telemetry and agentic risk

Overview

This skill coherently connects an agent to one Trello workspace through the official Trello MCP server, with disclosed OAuth setup and explicit approval requirements for writes.

Install this only if you want the agent connected to the selected Trello workspace. Treat the OAuth environment variables as secrets, rerun setup only after a fresh connection or credential rotation, and review each requested Trello write or archive action before approving it.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (1)

Credential Access

High
Category
Privilege Escalation
Content
## Authentication

Maverick performs MCP-native OAuth Authorization Code with PKCE and dynamic public-client registration, then seeds the access token, refresh token, and issued client id into mcporter's vault through `scripts/setup.sh`. mcporter uses OAuth protected-resource discovery when refreshing, which preserves Trello's `https://mcp.trello.com/v1` resource indicator.

Setup requires these credential variables:
Confidence
78% confidence
Finding
The skill explicitly relies on access tokens, refresh tokens, and client identifiers from environment variables and writes them into a local credential vault. While this is expected for OAuth-based setup, it creates a real secret-handling risk: environment-sourced credentials can be exposed through logs, process environments, misconfigured shell history, or broader local access, and vault overwrites may unintentionally replace fresher tokens.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.