Personal Goals

Security checks across malware telemetry and agentic risk

Overview

This skill appears to be a narrow personal goal tracker that stores goal notes locally, with privacy caveats but no evidence of hidden or harmful behavior.

Install only if you want an agent to maintain a persistent local record of your goals and progress. Avoid storing highly sensitive personal details unless you are comfortable with them being kept in knowledge/personal/goals.md, and review or delete that file when needed.

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
93% confidence
Finding
The trigger conditions are broad enough to activate on common phrases like 'plan', 'progress', 'deadline', or 'I want to', which can cause the skill to run in conversations where the user did not intend goal tracking or persistent memory access. In this skill, that matters because activation leads to reading and potentially updating a personal goals file, increasing the chance of inappropriate collection or modification of sensitive personal data.

Missing User Warnings

Medium
Confidence
98% confidence
Finding
The skill instructs the agent to persistently update `knowledge/personal/goals.md` whenever the user sets a new goal or reports progress, but it provides no requirement to notify the user, request consent, or distinguish ephemeral advice from long-term storage. Because this file contains sensitive personal life plans, deadlines, and progress, silent persistence creates a privacy and data-governance risk even if the author likely intended convenience rather than harm.

VirusTotal

65/65 vendors flagged this skill as clean.

View on VirusTotal