Talk Like TED

• Outcome: Pass
• Latest audit: Jun 5, 2026 at 9:48 AM UTC
• Version:
  1.0.0

Overview

This appears to be a presentation-coaching skill with broad but low-impact activation language, not a skill that asks for sensitive access or performs unsafe actions.

Install this if you want presentation and public-speaking advice framed around Talk Like TED. Be aware it may activate for broad presentation-related requests; ask your agent for neutral presentation advice when you do not want book-specific coaching.

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: 90% confidence
• Finding: The trigger list is very broad and includes common phrases like 'presentation', 'pitch', and 'public speaking tips', which can cause the skill to activate for many ordinary requests where the user did not specifically ask for this framework. Over-broad invocation can hijack routing, override more appropriate skills or base-assistant behavior, and increase the chance that users receive branded or book-constrained guidance when they wanted neutral help.

Vague Triggers

Medium

• Confidence: 85% confidence
• Finding: Saying the skill will appear whenever it 'senses this book could help' creates an open-ended activation condition with no clear boundary. That ambiguity encourages opportunistic invocation and makes it harder to predict or control when the skill takes over, which can degrade user autonomy and cause inappropriate routing.

VirusTotal

64/64 vendors flagged this skill as clean.