The Big Book Of Serial Killers

Security checks across malware telemetry and agentic risk

Overview

The available evidence shows a low-risk skill with only a minor activation-scope concern, not malicious behavior.

This appears acceptable to install based on the supplied evidence. Be aware it may activate on generic words like organized or disorganized; consider narrowing trigger phrases if unexpected activation would be disruptive.

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
95% confidence
Finding
The trigger list includes very broad standalone terms like "organized" and "disorganized," which are common words in ordinary conversation and can cause the skill to activate outside the user's intended topic. In an agent setting, this can hijack unrelated conversations, inject unwanted content, and increase the chance of unsafe or inappropriate true-crime material being surfaced unexpectedly.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal