Todoist

• Outcome: Pass
• Latest audit: May 27, 2026 at 9:04 PM UTC
• Version:
  0.1.1

Overview

This is a straightforward Todoist helper skill; its main risks are normal CLI installation and access to your Todoist tasks, not hidden or malicious behavior.

Install this only if you want your agent to use Todoist through the td CLI. Review or pin the upstream Todoist CLI before running the setup commands if you are cautious about supply-chain risk, and be aware that generic task or agenda requests may cause the agent to consult your Todoist data.

SkillSpector

By NVIDIA

Vulnerability Patterns

• Trigger Abuse: Overly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
• Prompt Injection: Instruction Override, Hidden Instructions, Exfiltration Commands
• Data Exfiltration: External Transmission, Env Variable Harvesting, File System Enumeration
• Privilege Escalation: Excessive Permissions, Sudo/Root Execution, Credential Access
• Supply Chain: Unpinned Dependencies, External Script Fetching, Obfuscated Code

Findings (1)

Vague Triggers

Medium

• Confidence: 87% confidence
• Finding: The skill’s trigger description is broad enough to activate on many ordinary requests about tasks, agendas, or checklists, which can cause the agent to invoke this skill in contexts the user did not intend. Because the skill supports state-changing operations such as add, update, complete, move, and delete, over-triggering increases the risk of unintended access to personal Todoist data or accidental modification of tasks.

VirusTotal

64/64 vendors flagged this skill as clean.