The Butchering Art

Security checks across malware telemetry and agentic risk

Overview

The available evidence points to a low-risk educational skill, with only a routing-scope concern about broad trigger words.

Before installing, check whether you want a history/book skill to activate on general terms like surgery or hygiene. The available evidence does not show malicious or high-impact behavior, but narrower triggers would make it less likely to appear in unrelated medical or cleanliness 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 (1)

Vague Triggers

Medium
Confidence
95% confidence
Finding
The trigger list is broad enough to match many ordinary, high-frequency topics such as surgery, hygiene, medical history, and innovation, which can cause this skill to activate outside the user's actual intent. Overbroad activation is dangerous because it can hijack routing, inject unsolicited onboarding content, and steer conversations toward this skill when another tool or a neutral response would be more appropriate.

VirusTotal

54/54 vendors flagged this skill as clean.

View on VirusTotal