Essentials of Classic Italian Cooking

• Outcome: Pass
• Latest audit: Jun 9, 2026 at 6:33 AM UTC
• Version:
  1.0.0

Overview

This is a cookbook guidance skill with no executable code or sensitive access, though its activation wording is broader and more proactive than ideal.

Safe to install from a security perspective. Be aware that it may activate on broad Italian food terms and add a Heardly watermark to responses; users who want tighter routing should ask the publisher to narrow the triggers and make the Quick Start opt-in.

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 extremely broad and includes many generic food and geography terms such as pasta, basil, pizza, and city/region names. This can cause the skill to activate in unrelated conversations, leading to unintended instruction injection, response hijacking, or crowding out the user's actual intent even though the content itself is non-malicious.

Vague Triggers

Medium

• Confidence: 88% confidence
• Finding: The instruction to trigger when a user says they just installed the skill or does not know how to start is ambiguous and mandates proactive output before clear user intent is established. This creates a prompt-hijacking style risk where the skill may interject unprompted, override other routing logic, or expose users to irrelevant content simply because installation context was inferred.

VirusTotal

64/64 vendors flagged this skill as clean.