test

Security checks across malware telemetry and agentic risk

Overview

This Trello helper is transparent about using your Trello credentials and provides manual commands, but some commands can change live Trello cards.

Install only if you want an agent to use your Trello API key and token. Treat create, move, comment, and archive commands as real changes to your Trello workspace, verify board/list/card IDs before running them, and keep the Trello token secret.

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: 91% confidence
Finding: The skill documents state-changing Trello operations including creating cards, moving cards, commenting, and archiving without an explicit warning that these actions modify remote user data. In an agent setting, this increases the chance of unintended destructive or irreversible changes because the commands are presented alongside read-only examples with no confirmation or safety guidance.

VirusTotal

65/65 vendors flagged this skill as clean.

View on VirusTotal