Agent Group

Security checks across malware telemetry and agentic risk

Overview

This skill only keeps a small local list of named agent-group members and does not show hidden network access, credential use, or destructive behavior.

Install if you are comfortable with this skill saving local group membership state. Use clear, intentional commands for creating or dissolving groups, and avoid putting sensitive information into group commands.

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 trigger phrases are extremely broad, short, and colloquial, such as creating a group, adding an agent, listing members, and dissolving the group. Without namespace, confirmation, or scope constraints, normal user conversation could unintentionally invoke the skill or cause agent-management actions in contexts where the user did not mean to operate this skill.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal