Back to skill

Security audit

Internet Conversion Os

Security checks for vulnerabilities and agentic risk

Overview

This is a Chinese-language marketing and conversion strategy skill with no executable code, hidden persistence, credential handling, or data access behavior.

Install this if you want a Chinese-language framework for conversion and growth strategy. Review whether its broad marketing scope and Chinese default fit your workflow; no hidden code execution or sensitive access was found.

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 skill description is scoped so broadly that it can activate for almost any marketing, growth, monetization, content, product positioning, trust-building, or user-journey request. Over-broad activation increases the chance of unintended routing, where this agent handles requests outside its safest or most appropriate boundary and may override more suitable specialized skills or system behavior.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
88% confidence
Finding

The skill metadata and body are written entirely in Chinese and present the skill as operating in that language, but there is no statement that users may choose another language or locale. Under the policy, forcing a specific language without opt-in is a natural-language policy concern unless the locale constraint is explicitly documented and justified.

Content

No source excerpt is available for this finding.