Tasktrove

Security checks across malware telemetry and agentic risk

Overview

Tasktrove is a straightforward Tasktrove API helper with disclosed network and token use, though users should be careful with state-changing and delete operations.

Install this only if you want an agent connected to your Tasktrove instance. Set TASKTROVE_HOST to a server you trust, protect TASKTROVE_TOKEN, prefer HTTPS or a trusted local network, and require explicit confirmation before completing, updating, or deleting tasks.

SkillSpector

By NVIDIA

Vulnerability Patterns

MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
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 (2)

Description-Behavior Mismatch

Medium

Confidence: 92% confidence
Finding: The skill metadata advertises listing, creating, completing, and updating tasks, but the documentation also exposes task deletion. An undeclared destructive capability is dangerous because users or orchestrators may invoke the skill under the assumption it cannot permanently remove data, increasing the risk of accidental or unauthorized destructive actions.

Missing User Warnings

Medium

Confidence: 95% confidence
Finding: Documenting a DELETE endpoint without any warning, confirmation step, or safeguard encourages unsafe destructive use. In a todo-management context, this can lead to permanent loss of task data from a self-hosted instance through accidental invocation, mistaken IDs, or automated tool misuse.

VirusTotal

66/66 vendors flagged this skill as clean.

View on VirusTotal