IM Framework

Security checks across malware telemetry and agentic risk

Overview

This skill is a philosophy reference aid that reads bundled reference data and public source pages, with no evidence of hidden execution or data theft.

Install this when you specifically want answers grounded in the Immanent Metaphysics framework. Be aware it may activate on broad philosophy or ethics wording, and verify whether the missing graph.jsonl and whitebook-map.jsonl files matter for your intended use.

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: 92% confidence
Finding: The trigger scope is broad enough to activate on generic terms like modality questions, ethics-related phrases, or requests to ground claims in the framework, which can cause the skill to be invoked outside narrowly intended contexts. Over-broad activation increases the chance that a user is funneled into a single philosophical source unnecessarily, creating relevance, reliability, and prompt-steering risk, especially because the skill strongly instructs the agent to treat one live website as canonical.

VirusTotal

65/65 vendors flagged this skill as clean.

View on VirusTotal