Lamb

Security checks across malware telemetry and agentic risk

Overview

This appears to be a low-risk book companion skill with only minor risk of being invoked too broadly.

Installers should expect a book discussion and self-reflection aid. Use explicit prompts that mention Lamb, Christopher Moore, Biff, or Joshua to avoid accidental activation in unrelated conversations.

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 (2)

Vague Triggers

Medium

Confidence: 93% confidence
Finding: The trigger condition explicitly activates when a user says they 'just installed this skill' or 'doesn't know how to start,' which are generic onboarding/help-seeking phrases not uniquely tied to this book domain. That can cause unintended routing of unrelated conversations into this skill, creating prompt-scope hijacking at the orchestration layer and increasing the chance of irrelevant or unsafe advice being injected into benign sessions.

Vague Triggers

Low

Confidence: 86% confidence
Finding: The suggested invocation 'Map this book to my life' is broad and reusable across many reading or self-help contexts, so it is not a strong, unique selector for this specific skill. If the platform uses such phrases for matching or user guidance, it can lead to accidental invocation and inappropriate personalization based on the wrong skill context.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal