Security audit

荣格思维视角

Security checks for vulnerabilities and agentic risk

Overview

This is a Markdown-only Jung-style roleplay skill; the main cautions are mental-health-adjacent advice and broad triggers, not malicious behavior.

Install only if you want a Jungian reflective roleplay experience. Do not use it as a substitute for a licensed mental health professional, diagnosis, treatment, or crisis support, and be aware that broad psychology or dream-related prompts may activate it unless you explicitly exit roleplay.

A.I.G

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

SkillSpector

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 (6)

Missing User Warnings

Medium

Category: Not specified by scanner
Confidence: 97% confidence
Finding: The skill explicitly targets psychological analysis, self-exploration, and dream interpretation, but it does not provide a robust safety warning or boundaries around mental health use. This is dangerous because users may treat the roleplayed Jung persona as authoritative guidance for distress, delusions, trauma, or other mental-health-sensitive issues, especially since the skill encourages deep inward interpretation and symbolic meaning-making.
Content: No source excerpt is available for this finding.

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 95% confidence
Finding: The trigger list includes very broad, everyday terms such as “心理学”, “梦境”, and “无意识”, which can cause the skill to activate in contexts where the user did not specifically request Jung-style roleplay or psychologically framed analysis. In this skill, unintended activation is more concerning because the content steers users into sensitive self-exploration and dream interpretation, increasing the chance of inappropriate or misleading responses in ordinary conversations.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium

Category: Not specified by scanner
Confidence: 83% confidence
Finding: The entire skill reference file is written exclusively in Chinese and is explicitly intended for use in creating a "荣格思维视角" skill. This can constitute a language/locale policy issue because it presents the skill behavior and content in a fixed language without indicating that users may choose another language or opt in to Chinese output.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium

Category: Not specified by scanner
Confidence: 96% confidence
Finding: This markdown file is written entirely in Chinese, including the title and all user-facing content, and nowhere indicates that Chinese is optional or that the skill supports multiple languages. For a general-purpose background reference used by an AI skill, this creates a language/locale policy concern because it implicitly constrains outputs or usage to a single language without user opt-in.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Low

Category: Not specified by scanner
Confidence: 72% confidence
Finding: The skill instructions are written to enforce a fixed response style and include a hardcoded English disclaimer phrase, but do not state that the user may choose their preferred language. This can create a locale/language policy issue because the skill appears to impose language behavior without explicit user opt-in.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Low

Category: Not specified by scanner
Confidence: 84% confidence
Finding: This markdown file contains user-facing natural language exclusively in Chinese, and there is no indication that the reader can choose another language or that the document is intentionally limited to a Chinese-speaking audience. Under the language/locale policy rule, forcing a specific language without opt-in can be a policy concern.
Content: No source excerpt is available for this finding.