Back to skill

Security audit

Lab2startup Tech Market Fit

Security checks for vulnerabilities and agentic risk

Overview

This is a plain Chinese guidance skill for technology-market fit analysis, with no code execution, data access, persistence, or hidden behavior.

Installers should expect a Chinese-language advisory skill for startup technology-market fit strategy. Consider narrowing triggers or adapting language if the skill will be used in multilingual or broad business contexts.

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 (2)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
91% confidence
Finding

The trigger list contains broad phrases such as '应用场景' and '转型策略' that can appear in many ordinary business or educational conversations, increasing the chance of unintended skill activation. This is not a code-execution issue, but it can misroute user requests, override better-matched skills, and cause confusing or irrelevant responses.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The skill content and description are entirely in Chinese and implicitly constrain the interaction language without checking the user's preference. If activated for a user operating in another language, it can reduce usability, distort analysis outputs, and create misunderstandings in a decision-support context.

Content

No source excerpt is available for this finding.