Back to skill

Security audit

峰哥解答万物

Security checks for vulnerabilities and agentic risk

Overview

This is a Chinese-language entertainment roleplay skill that may sound abrasive, but I found no hidden data access, persistence, or unsafe execution behavior.

Install this only if you want a Chinese-language roleplay persona with blunt, sarcastic outputs. Avoid using it for serious relationship, mental-health, or sensitive personal advice, and disable it if it activates outside explicit roleplay use.

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 (9)

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
91% confidence
Finding

The README describes the skill as a Chinese-language roleplay persona and all activation phrases, examples, and usage principles are written to drive Chinese-only behavior without mentioning any user consent, fallback language, or opt-in. This can override a user's expected language preference and degrade transparency, especially if the host agent activates the skill broadly or automatically.

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 is documented entirely as a Chinese-language persona and its activation phrases and examples assume Chinese-only interaction, with no indication that users can choose another language. This is primarily an accessibility and UX safety issue rather than a classic security flaw, but it can cause misleading behavior, reduced transparency, or unusable outputs for users who do not understand Chinese.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
92% confidence
Finding

The skill explicitly steers the model toward demeaning and potentially offensive phrasing, including insults or reductive judgments such as labeling users as '性压抑' and using '高嘲讽模式', but it does not warn users that outputs may be insulting or stigmatizing. In a roleplay setting this increases the chance of unexpected harmful content, especially for advice-seeking users discussing relationships, class, or personal insecurity.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
91% confidence
Finding

This JSON knowledge base is entirely organized with Chinese-language category labels and Chinese text content, with no indication that users can choose another language or locale. Under the policy rule for all file types, hard-coding a single language without documented opt-in can violate language/locale requirements.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
91% confidence
Finding

This JSON transcript includes the phrase "一个五百日元" (500 Japanese yen), which hardcodes a specific currency/locale in the content without any indication of user choice or region-specific justification. Under the policy rule for natural-language locale constraints, fixed locale-specific wording can violate organizational language/locale policy when no opt-in or justification is provided.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
90% confidence
Finding

This JSON file stores all natural-language content in Chinese, with no indication that the user can choose another language or locale. Under the stated policy, forcing a specific language without opt-in is a natural-language policy violation unless the locale constraint is clearly documented and justified.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
90% confidence
Finding

This code embeds extensive Chinese-only natural-language instructions and activation text, effectively forcing a specific language mode on users. Under the policy, language or locale constraints should not be imposed without opt-in unless clearly documented and justified.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
91% confidence
Finding

This JSON knowledge-base file stores natural-language content entirely in Chinese, and there is no accompanying indication in the file that the language is optional, selectable, or limited to a justified region-specific context. Under the language/locale policy rule, hard-coding a specific language without opt-in can be a policy concern even in data/config-style files.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
78% confidence
Finding

The JSON transcript includes the phrase "咱们中国讲究这个...", which frames guidance through a China-specific normative lens. For a general-purpose knowledge base entry, this can amount to an implicit locale assumption without any opt-in or justification for restricting the perspective to a specific national context.

Content

No source excerpt is available for this finding.