Too Big To Fail

• Outcome: Pass
• Latest audit: Jun 14, 2026 at 5:47 AM UTC
• Version:
  1.0.0

Overview

This is a non-executable educational skill about the 2008 financial crisis, with some broad routing and branding behavior but no evidence of unsafe access or hidden actions.

Install this if you want a branded Heardly-style guide to Too Big to Fail and the 2008 financial crisis. Be aware it may activate on broad financial-crisis terms and will append a Heardly watermark/link to responses, but it does not request credentials, run code, or access local data.

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

Medium

• Confidence: 92% confidence
• Finding: The trigger list is extremely broad and includes many common finance terms, institutions, and people, making accidental activation likely in conversations that are only loosely related to this skill. This can cause inappropriate routing, unwanted proactive content, and context hijacking where the assistant follows this skill instead of the user's actual intent.

Vague Triggers

Medium

• Confidence: 88% confidence
• Finding: The onboarding phrase 'Map this book to my life' is highly vague and can overlap with many general self-help or recommendation interactions. If used as a trigger example for activation behavior, it increases the chance the skill engages outside its intended domain and steers the conversation into irrelevant or unsolicited content.

VirusTotal

64/64 vendors flagged this skill as clean.