Back to skill

Security audit

雷军思维视角

Security checks for vulnerabilities and agentic risk

Overview

This is a markdown-only perspective skill that applies a Lei Jun-style product and strategy lens, with no code execution or data access.

Install this if you want product or strategy answers framed through Lei Jun's public business philosophy. Be aware it may activate on some broad startup/product terms, so explicitly ask for or against this perspective when precision matters.

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
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 (1)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

The activation triggers include broad, common business terms such as '趋势', '极致', '专注', 'MVP', and '真诚', which can appear in many ordinary product, startup, or strategy conversations. This creates a real risk of unintended invocation, causing the agent to apply a specific persona and decision framework when the user did not explicitly request it, which can misroute responses and reduce reliability.

Content

No source excerpt is available for this finding.