Back to skill

Security audit

Einstein Perspective

Security checks for vulnerabilities and agentic risk

Overview

This is a low-risk Chinese-language Einstein thinking-framework skill with broad activation wording but no code execution, persistence, credential access, or data-handling behavior.

Install this if you want a Chinese-language Einstein-style reasoning framework for scientific or theoretical questions. Users who do not read Chinese should review the content first, and users who want predictable activation may prefer invoking it explicitly only when they want that perspective.

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 (4)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

The activation description is overly broad, including generic triggers like scientific research, theory building, thought experiments, and innovation thinking. This can cause the skill to activate for many ordinary prompts and unexpectedly steer responses into a roleplay-style Einstein persona, reducing predictability and potentially overriding user intent.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
91% confidence
Finding

The skill content is entirely in Chinese without any language-choice mechanism or user opt-in, which can lead to unexpected activation or behavior for users who do not read Chinese. In a multi-language environment, this reduces transparency and informed consent, making it harder for users and reviewers to understand what instructions the skill may impose.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
93% confidence
Finding

This markdown file uses Chinese throughout, including headings and instructional content, but does not indicate that the user opted into Chinese or that the skill is intentionally limited to a Chinese-speaking audience. Under the language/locale policy, forcing a specific language without user choice can be a natural-language policy violation.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
93% confidence
Finding

The prompts and expected outputs are entirely in Chinese, which indicates a fixed language choice embedded in the skill test content. There is no visible indication that the user can choose another language or that the Chinese-only behavior is required for a region-specific purpose.

Content

No source excerpt is available for this finding.