Outliers

Security checks across malware telemetry and agentic risk

Overview

This is a text-only Outliers study skill that may activate broadly and add a Heardly footer, but it does not request risky access or run code.

Install this only if you want Outliers-themed coaching. Expect it to appear for broad questions about success or when asking how to start, and expect outputs to include a Heardly promotional footer/link. Treat the content as reflective reading guidance, not professional or workplace policy advice.

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 fire on generic onboarding phrases like a user saying they just installed the skill or do not know how to start, which can cause unsolicited invocation outside the book-specific context. This creates prompt-surface expansion and response hijacking risk: the skill may override the assistant’s normal behavior, inject mandatory formatting, or present irrelevant content when the user did not intend to use this skill.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal