Agent Task Tracker

• Outcome: Pass
• Latest audit: May 29, 2026 at 8:21 PM UTC
• Version:
  1.1.1

Overview

This skill is a transparent local task tracker, but users should be careful because it records task details and command context across sessions.

Install this only if you want automatic local task tracking across sessions. Review memory/tasks.md periodically, and avoid storing tokens, credentials, private user content, sensitive hostnames, or full commands containing secret arguments.

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 (3)

Vague Triggers

Medium

• Confidence: 91% confidence
• Finding: The skill is configured to trigger on essentially every task lifecycle event and is described as automatic rather than user-invoked. That broad scope increases the chance of unintended activation and persistent writes for tasks where tracking is unnecessary or inappropriate, which can amplify privacy and data-retention risks.

Missing User Warnings

Medium

• Confidence: 95% confidence
• Finding: The skill directs the agent to persist task state in memory/tasks.md as a 'single source of truth' but provides no user-facing notice or consent mechanism for storing conversation-derived state across sessions. This creates a real privacy risk because users may not expect task details to be retained beyond the immediate interaction.

Missing User Warnings

Medium

• Confidence: 98% confidence
• Finding: Requiring storage of session ID, PID, server name, and full command can expose sensitive operational context, including infrastructure identifiers and command-line arguments that may contain secrets, paths, or internal hostnames. Persisting this information in a resumable file increases the blast radius of any later disclosure or misuse.

VirusTotal

65/65 vendors flagged this skill as clean.