ClawHub
Back to skill

Security audit

Sam Altman AI创业思维

Security checks for vulnerabilities and agentic risk

Overview

This is a Chinese-language strategy framework skill for analyzing AI startup opportunities, with no evidence of hidden execution, data access, persistence, or exfiltration.

Install this if you want Chinese-language guidance for AI startup and opportunity analysis. Be aware it may answer in Chinese and could activate on broader AI-strategy prompts than intended.

A.I.G

Vulnerability Patterns
  • Skill Instruction HijackingAlters the agent's session goals or safety constraints when the skill loads
  • Agent Memory PoisoningWrites attacker-controlled rules into memory that affect later sessions
  • Remote Payload Retrieval and ExecutionFetches external code whose behavior can change after review
  • Embedded Malicious CodeShips malicious scripts inside the skill and executes them locally
  • Unauthorized Access and Privilege EscalationObtains permissions beyond the task's legitimate needs

SkillSpector

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
95% confidence
Finding
The activation scope is broad enough that common AI-related terms could trigger this skill in contexts where the user did not ask for a Sam Altman-style startup analysis. This can cause unintended routing, reduce response quality, and potentially override more appropriate skills, though it does not directly introduce code execution or data exfiltration risk.

Natural-Language Policy Violations

Medium
Confidence
86% confidence
Finding
The skill is authored entirely in Chinese and does not offer a language fallback or clearly state that it is intended only for Chinese-language users. In mixed-language environments, this can lead to unintended language switching, user confusion, and degraded accessibility, especially if the skill activates for non-Chinese prompts.

Static analysis

No suspicious patterns detected.