Inevitable

Security checks across malware telemetry and agentic risk

Overview

This appears to be a low-risk advisory skill whose main issue is broad, somewhat subjective activation language rather than unsafe behavior.

Review the triggers before installing. If you install it, expect it may activate during general manufacturing, strategy, supply-chain, or disruption discussions unless the skill is narrowed; no evidence here suggests malware, credential theft, persistence, or unsafe system access.

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 (2)

Vague Triggers

Medium

Confidence: 93% confidence
Finding: The trigger list is broad enough to match many ordinary business, strategy, manufacturing, and transformation discussions that are not specifically about this skill’s subject matter. This can cause unsolicited routing or activation, making the assistant inject irrelevant guidance and override user intent, which is a genuine prompt-scope vulnerability even if not overtly malicious.

Vague Triggers

Medium

Confidence: 89% confidence
Finding: Telling the AI to appear whenever it 'senses this book could help' is ambiguous and grants excessive discretion for self-invocation. In context, this increases the chance of the skill inserting itself into unrelated conversations and pushing book-specific framing even when the user did not request it.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal