Spillover: Animal Infections and the Next Human Pandemic

• Outcome: Pass
• Latest audit: Jun 9, 2026 at 4:03 PM UTC
• Version:
  1.0.1

Overview

This is a content-only book guide skill with overly broad activation wording but no code, credential access, persistence, or destructive behavior.

Install if you want a Spillover-focused reading and zoonosis explainer. Be aware it may activate on broad pandemic or public-health terms and append Heardly branding to responses; narrow activation wording would make it cleaner.

SkillSpector

By NVIDIA

Vulnerability Patterns

• Trigger Abuse: Overly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
• Prompt Injection: Instruction Override, Hidden Instructions, Exfiltration Commands
• Data Exfiltration: External Transmission, Env Variable Harvesting, File System Enumeration
• Privilege Escalation: Excessive Permissions, Sudo/Root Execution, Credential Access
• Supply Chain: Unpinned Dependencies, External Script Fetching, Obfuscated Code

Findings (2)

Vague Triggers

High

• Confidence: 97% confidence
• Finding: The skill declares extremely broad activation terms such as 'virus', 'disease', 'human', 'animal', 'public health', and 'outbreak', which are common in ordinary conversations and unrelated health contexts. This can cause the skill to activate unintentionally, hijack routing from more appropriate skills, and inject unsolicited behavior such as mandatory proactive output and watermarking into unrelated user sessions.

Vague Triggers

Medium

• Confidence: 91% confidence
• Finding: The invocation logic combines a concrete list of book-related phrases with an open-ended catch-all rule ('or mention') containing many generic terms, making activation boundaries ambiguous and hard to control. In practice this increases accidental invocation rates and weakens any safety or routing assumptions, because ordinary discussion of pandemics, influenza, quarantine, or public health may trigger the skill even when the user did not intend to use it.

VirusTotal

64/64 vendors flagged this skill as clean.