Leave Doc

Security checks across malware telemetry and agentic risk

Overview

This is a local leave-document generator with no network or credential behavior, though one extra helper script can keep local logs if invoked.

Use the documented scripts/doc.sh commands for leave documents. Avoid putting sensitive personal or medical details into scripts/script.sh unless you are comfortable with those values being stored in local log files under the leave-doc data directory.

SkillSpector

By NVIDIA

Vulnerability Patterns

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
Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep

Findings (1)

Missing User Warnings

Medium

Confidence: 87% confidence
Finding: The script persistently stores user-provided content in data.log and also records command history in history.log under a user directory without clearly warning users in the help output. In an agent-skill context, this can capture sensitive prompts, identifiers, or operational data unexpectedly, increasing privacy and data exposure risk if local files are later accessed by other processes or users.

VirusTotal

66/66 vendors flagged this skill as clean.

View on VirusTotal