taskleef

• Outcome: Pass
• Latest audit: May 27, 2026, 9:19 PM
• Version:
  1.0.1

Overview

This is a coherent Taskleef task-management skill, but users should review the downloaded CLI and be careful with delete or clear commands.

Install only if you intend to let the agent manage your Taskleef account. Review the downloaded todo CLI before running it, keep TASKLEEF_API_KEY out of repos and logs, and require explicit confirmation before delete, project delete, or board clear actions.

SkillSpector

By NVIDIA

Vulnerability Patterns

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

Findings (5)

Vague Triggers

Medium

• Confidence: 86% confidence
• Finding: The README encourages broad natural-language requests such as adding, completing, and moving tasks without clarifying confirmation boundaries or requiring precise user intent. In an agent skill context, this can increase the chance of unintended invocation or accidental modification of remote Taskleef data when ambiguous user phrasing is interpreted as an action.

Missing User Warnings

Medium

• Confidence: 92% confidence
• Finding: The README describes capabilities that add, complete, delete, and reorganize remote todos and boards, but it does not warn that these operations change persistent server-side data. In an agent-integrated environment, lack of disclosure about destructive behavior raises the risk of users triggering unintended changes without understanding the consequences.

Vague Triggers

Medium

• Confidence: 92% confidence
• Finding: The skill description is broadly phrased around common task and project-management activities, which increases the chance the agent will invoke this skill for many ordinary requests. Because the skill can perform authenticated remote actions such as adding, completing, deleting, and clearing items, overbroad activation can cause unintended state-changing operations on a user's Taskleef account.

Missing User Warnings

Medium

• Confidence: 95% confidence
• Finding: The documentation presents destructive commands like delete and clear without warning about irreversible or state-altering effects. In an agent setting, this omission can normalize unsafe execution and increase the risk that the assistant performs deletion or bulk-clearing actions without sufficient confirmation or user awareness.

Missing User Warnings

Low

• Confidence: 82% confidence
• Finding: The skill relies on an API key and remote service access but does not warn that task contents and identifiers will be transmitted to Taskleef over the network. This is risky because users may provide sensitive task data, and the absence of a privacy/network notice can lead to unintentional disclosure to a third-party service.

VirusTotal

66/66 vendors flagged this skill as clean.