Track

Security checks across malware telemetry and agentic risk

Overview

This is a local habit-tracking skill that stores personal progress data on disk, with no evidence of network access, credential use, or destructive behavior.

Install only if you are comfortable keeping habit and goal history in local JSON files under memory/track. Review or delete that folder when you no longer want the history retained, and be aware that only the habit logging helper is included in this version.

SkillSpector

By NVIDIA

Vulnerability Patterns

Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access

Findings (2)

Lp3

Medium

Category: MCP Least Privilege
Confidence: 92% confidence
Finding: The skill explicitly directs use of local files under `memory/track/` and invokes scripts that read and write habit, goal, streak, and metrics data, yet no permissions are declared. This creates an authorization and transparency gap: the skill can persist sensitive personal data without an explicit permission boundary, making misuse or unexpected data access harder to govern.

Vague Triggers

Medium

Confidence: 79% confidence
Finding: The trigger language is very broad—covering habits, goals, progress, streaks, and accountability—which overlaps with many ordinary conversations. Overbroad activation can cause the skill to engage unexpectedly and collect or store sensitive self-improvement, health-adjacent, or financial goal data in contexts where the user did not clearly intend to start persistent tracking.

VirusTotal

63/63 vendors flagged this skill as clean.

View on VirusTotal