Back to skill

Security audit

Elon Musk Perspective V2

Security checks for vulnerabilities and agentic risk

Overview

This is a Chinese-language persona/thinking-framework skill with no code execution, credential access, network use, or persistence, though its activation phrases and first-person persona style are broad enough to merit user awareness.

Install this only if you want Chinese-language responses framed through a Musk-inspired persona. Be aware that broad phrases like first principles may activate the style unintentionally, and outputs should be treated as a simulation based on public information rather than Elon Musk's real views.

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
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (5)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
92% confidence
Finding

The trigger list includes broad, commonly used phrases such as “第一性原理”, “马斯克会怎么看”, and “perspective”, which can appear in normal conversation without deliberate intent to activate a persona skill. This can cause unintentional activation and steer responses into a preset framing, increasing the risk of instruction collision, unwanted style takeover, or bypass of the user’s actual requested mode.

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 states that once activated it will respond in Musk’s first-person voice and a fixed rhetorical style, without offering user choice on language or presentation. While not directly enabling code execution or data exfiltration, this can override user intent, reduce transparency, and make outputs more manipulative or misleading by presenting a simulated authoritative persona as the default response mode.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

This markdown file is entirely written in Chinese, including the title and all test descriptions, with no indication that the user can choose another language or that the skill is intentionally limited to a Chinese-speaking context. Under the policy rules, forcing a specific language without opt-in is 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
88% confidence
Finding

The entire skill file is presented only in Chinese, including the title and all descriptive content, with no indication that users can choose another language or that the skill is intentionally limited to a Chinese-speaking audience. Under the language/locale policy, forcing a specific language without user opt-in 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
89% confidence
Finding

This markdown file presents all user-facing content in a single language, which can amount to a language/locale policy issue when no opt-in or justification is provided. The file does not indicate that Chinese is required, optional, or limited to a region-specific audience.

Content

No source excerpt is available for this finding.