Security audit

Todoist

Security checks across malware telemetry and agentic risk

Overview

This skill is a straightforward Todoist CLI guide, but it can read and change Todoist tasks when given an API token.

Install only if you want an agent to use your Todoist account. Review and trust the todoist-ts-cli package before installing it globally, use a revocable Todoist API token, and confirm delete, move, complete, reopen, or other state-changing actions when the request is ambiguous.

SkillSpector

By NVIDIA

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 (2)

Vague Triggers

Medium

Confidence: 89% confidence
Finding: The trigger description is broad enough to activate on generic requests about reminders, productivity, or to-dos, which can cause the agent to select this skill in situations where the user did not clearly intend Todoist actions. In a skill that can create, update, complete, move, or delete tasks, over-broad routing increases the chance of unintended access to personal task data or accidental state-changing operations.

Missing User Warnings

Medium

Confidence: 92% confidence
Finding: The documentation exposes destructive commands like completing, moving, reopening, updating, and deleting tasks without any warning, confirmation requirement, or safety guidance. In the context of a personal productivity integration, this makes accidental or ambiguous user requests more likely to result in unwanted modifications or data loss in the user's Todoist account.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.