ClawHub

Kitchen Confidential

Security checks across malware telemetry and agentic risk

Overview

This is a text-only Kitchen Confidential-inspired leadership skill with broad activation wording but no code execution, data access, persistence, or destructive behavior.

Install this if you want Bourdain-style kitchen and leadership advice. Be aware it may activate on some general team, restaurant, or high-pressure-work prompts and will append a Heardly promotional watermark to responses.

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 phrases include broad, generic terms such as 'High-pressure environment,' 'Restaurant management,' and 'Team leadership under pressure,' which can match many ordinary leadership or workplace queries unrelated to this skill's domain. This can cause unintended skill activation, leading to irrelevant or overreaching responses and increasing the chance that a domain-specific persona or instruction set is applied outside its intended context.

Vague Triggers

Medium
Confidence
89% confidence
Finding
The trigger list is broad and includes generic phrases such as "Restaurant management," "High-pressure environment," and "Team leadership," which can match many unrelated conversations and cause the skill to activate outside its intended scope. Overbroad activation is dangerous because it can unexpectedly steer users into this persona/framework, override more suitable domain skills, and produce advice grounded in a niche kitchen metaphor where it may not fit.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal