On Intelligence

Security checks across malware telemetry and agentic risk

Overview

This is a benign educational skill about Jeff Hawkins's On Intelligence, with the main caveat that its broad trigger terms may make it activate in unrelated AI or intelligence discussions.

Install this if you want a guided explanation of On Intelligence and Hawkins-style brain-based AI ideas. Be aware it may activate on generic terms like AI, AGI, prediction, or intelligence, so you may need to disable or ignore it when those words are used outside this book context.

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: 97% confidence
Finding: The trigger list is excessively broad and includes generic terms such as "prediction," "intelligence," "AI," and "AGI," plus a fallback trigger for users who "just installed this skill or doesn't know how to start." This can cause the skill to activate in many unrelated conversations, overriding more appropriate skills or injecting off-topic guidance unexpectedly; while not a code-execution issue, it is a genuine security/quality problem because broad activation increases the attack surface for prompt interference and unintended behavior.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal