Failing Forward

Security checks across malware telemetry and agentic risk

Overview

This is a text-only self-improvement coaching skill with broad activation wording but no hidden code, credential use, or system access.

Install this if you want a Failing Forward-style coaching framework to influence conversations about failure, setbacks, resilience, and persistence. Expect proactive onboarding and a branded Heardly watermark in responses; do not treat it as professional mental health, legal, financial, or crisis support.

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 very broad and includes common terms like 'failure,' 'resilience,' 'persistence,' and 'learning from mistakes,' which can cause the skill to activate in many ordinary conversations where the user did not intend to invoke this book-specific framework. Overbroad activation can lead to inappropriate interception of unrelated discussions, reduced user control, and accidental application of rigid guidance in emotionally sensitive contexts.

Vague Triggers

Medium

Confidence: 88% confidence
Finding: The Quick Start promise that the skill will appear whenever it 'senses this book could help' establishes an ambiguous, subjective activation rule that is not auditable or bounded. In a coaching or emotional-support context, this increases the chance of unsolicited intervention during sensitive conversations, which may confuse users or override more appropriate handling.

VirusTotal

61/61 vendors flagged this skill as clean.

View on VirusTotal