voc

Security checks across malware telemetry and agentic risk

Overview

This skill is a small vocabulary-study helper whose executable scripts only print informational placeholder text, with no evidence of data collection, network access, persistence, or destructive behavior.

Before installing, be aware that the skill can run its bundled shell scripts and may activate on general vocabulary-learning requests. The current scripts are harmless placeholders, but future versions should still be reviewed for any added file access, network calls, or mutations.

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: 91% confidence
Finding: The skill advertises very broad natural-language activation phrases such as mentioning "voc" or asking about vocabulary learning, decks, or stats, which can cause the router to invoke this skill in contexts the user did not intend. Because the skill has exec permission and is documented to call a helper script, unintended invocation increases the risk of unnecessary command execution, confusing responses, or accidental exposure of local behavior.

VirusTotal

63/63 vendors flagged this skill as clean.

View on VirusTotal