Grovo

Security checks across malware telemetry and agentic risk

Overview

The skill appears to be a disclosed Grovo/LinkedIn Learning integration, with broad wording but no evidence of hidden or malicious behavior.

Before installing, confirm you intend to let the agent work with Grovo/LinkedIn Learning data through the described integration. Review any requested account connection or OAuth flow, and use it only for tasks involving that service.

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: 90% confidence
Finding: The skill description is overly broad: 'Manage data, records, and automate workflows' could match many generic enterprise tasks, causing the agent to invoke this skill outside of clearly Grovo-specific requests. Overbroad routing increases the chance of unnecessary external-system access, unintended data exposure, or execution of actions against the wrong integration context.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal