Anthropic Founder Handbook

• Outcome: Pass
• Latest audit: Jun 9, 2026 at 4:03 PM UTC
• Version:
  1.0.0

Overview

This is a Chinese startup-advice skill with broad activation wording, but it contains only guidance documents and no hidden execution or data access.

Install this if you want Chinese-language startup coaching and founder-methodology checklists. Be aware that its activation wording is broad and mandatory, so it may be invoked in many startup or business-planning conversations; there is no artifact-backed evidence of hidden code execution, credential handling, persistence, or destructive behavior.

SkillSpector

By NVIDIA

Vulnerability Patterns

• Prompt Injection: Instruction Override, Hidden Instructions, Exfiltration Commands
• Trigger Abuse: Overly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
• 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

High

• Confidence: 95% confidence
• Finding: The skill description mandates use for a very broad class of entrepreneurship-related conversations, which can cause the agent to invoke this skill even when the user's request is only tangentially related. Over-broad mandatory activation increases the chance of inappropriate routing, response hijacking, and suppression of more relevant instructions or user preferences.

Natural-Language Policy Violations

Medium

• Confidence: 90% confidence
• Finding: The description is written to force a specific language/context without offering user choice or opt-in, which can override the user's preferred language or interaction mode. This can degrade reliability and create prompt-routing issues where the model follows the skill's language constraint instead of the user's request.

VirusTotal

60/60 vendors flagged this skill as clean.