Back to skill

Security audit

Ultimate Horizontal Timeline Architect

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed report-formatting template that turns suitable Chinese project content into a styled HTML timeline without adding code execution, data access, persistence, or privileged behavior.

Install this if you want Chinese executive-report or project-one-pager content rendered as a polished HTML timeline. Be aware it may impose its Chinese wording cleanup and HTML template even when you only intended a plain summary, so invoke it when that presentation style is desired.

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
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • 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
94% confidence
Finding

The trigger conditions are broad: generic requests like '向上汇报' or '项目一页纸' can match many unrelated user tasks and silently route them into this skill. That increases the chance of unintended activation, causing the agent to override normal response behavior, impose a rigid HTML rendering path, and transform content in contexts where the user did not request this format.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
89% confidence
Finding

The skill is written to enforce Chinese-language behavior and a specific output style without clear user opt-in. This can override user preferences or system expectations, leading to unwanted language switching and reducing reliability in multilingual or policy-sensitive environments where the agent should preserve the user's requested language and format.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.