DocsAutomator

Security checks across malware telemetry and agentic risk

Overview

This skill is a coherent DocsAutomator connector that discloses its credential use and requires user confirmation before state-changing document creation.

Install this only if you want the agent to operate your DocsAutomator workspace through OOMOL. Read/list actions can expose workspace automation details, and create-document actions can generate documents or consume service resources, so confirm payloads before allowing writes.

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 (1)

Vague Triggers

Medium

Confidence: 89% confidence
Finding: The skill description says to use this skill for ANY DocsAutomator request, which is an overly broad trigger that can cause the agent to invoke this skill by default for all DocsAutomator-related tasks without sufficient task-specific validation. That increases the chance of unintended execution paths, especially because the skill supports both read and state-changing actions and relies on downstream confirmation behavior rather than strict invocation scoping.

VirusTotal

63/63 vendors flagged this skill as clean.

View on VirusTotal