Back to skill

Security audit

Feynman Perspective V2

Security checks for vulnerabilities and agentic risk

Overview

This is a Chinese-language educational style skill that changes explanation framing but does not request tools, credentials, persistence, file access, or system privileges.

Install this if you want Chinese-language Feynman-style explanations. Be aware that broad trigger words like “简化” may activate the style when you only meant a normal simplification request.

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 (7)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The trigger list includes broad, common terms such as '简化' that may appear in many ordinary user requests, creating a real risk of unintended skill activation. This is not code-execution dangerous, but it can cause prompt-routing errors, unexpected persona injection, or interference with unrelated tasks.

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 defines behavior and output style entirely in Chinese and does not provide language negotiation or a justified locale restriction. In a multilingual assistant, this can cause unintended language switching, confuse users, and make responses less transparent or controllable, though it is primarily a safety and usability issue rather than a direct security compromise.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The trigger phrases are broad, generic terms such as '简化' and '费曼学习法' that can easily appear in ordinary user requests, causing accidental activation of the skill outside the user's intent. This can unpredictably override the assistant's normal behavior and route benign conversations into a persona-driven response mode, reducing reliability and user control.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
90% confidence
Finding

This markdown file presents all user-facing content exclusively in Chinese, and there is no indication that the user can choose another language or that the file is intentionally limited to a Chinese-speaking or region-specific audience. Under the language/locale policy rule, 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
87% confidence
Finding

This markdown file presents all user-facing content exclusively in Chinese, with no indication that another language can be selected or that the locale restriction is intentional. Under the stated policy, language-specific behavior 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
82% confidence
Finding

The skill metadata and content are presented entirely in Chinese, including trigger phrases, without indicating that language is optional or user-selectable. Under the language/locale policy, forcing a specific language without opt-in can be a natural-language policy violation unless the locale restriction is explicitly justified.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
94% confidence
Finding

The entire markdown file is written in Chinese, beginning with the title on L01, and there is no indication that the language choice is optional or tied to a region-specific requirement. Under the natural-language policy rules, forcing a specific language without user opt-in can be a locale-policy violation.

Content

No source excerpt is available for this finding.