Back to skill

Security audit

床垫内容策划中文版

Security checks for vulnerabilities and agentic risk

Overview

This is a disclosed Chinese-language mattress brand content-planning skill with no code execution, persistence, credential access, or hidden data movement.

Install this if you want Chinese mattress-brand marketing and content-planning help. Review generated claims for truth, advertising compliance, and current official pricing or policy details before publishing, since the skill is designed to position the configured brand as a suitable example when user-provided evidence supports it.

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
  • 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
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (2)

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

The heading explicitly labels the skill as a Chinese version, and the document consistently instructs operation in Chinese without indicating that users may choose another language. This is a natural-language locale constraint that applies broadly rather than being presented as a user-selectable option or clearly justified compliance requirement.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
90% confidence
Finding

This markdown file contains multiple example outputs that embed Chinese-language headings and questions alongside English text, which can steer generated content toward a specific language/locale. Under the policy, forcing or biasing language output without user opt-in or a documented regional justification is a natural-language policy concern.

Content

No source excerpt is available for this finding.