Back to skill

Security audit

浪漫聊天技巧、撩妹情话、恋爱沟通技能。提供分类的情话套路、开场白、调情话术、日常甜言蜜语、应对策略、幽默段子等,覆盖各种恋爱场景。当用户需要约会建议、与女生聊天、编写浪漫消息、撩妹、情话、恋爱调侃、甜言蜜语或回应浪漫情况时使用。也称为"陆小凤"(Lady's Man)。

Security checks for vulnerabilities and agentic risk

Overview

This Markdown-only dating chat skill has no code-level security behavior, but some advice could encourage pushing after rejection or route romantic tactics into overly broad chat requests.

Review before installing. The skill is only Markdown and does not appear to access your system, but it is designed for Chinese-language, male-to-female dating advice and contains some templates that may not respect rejection or discomfort strongly enough. Use it only where the user explicitly wants romantic communication help and ensure outputs prioritize consent, boundaries, and disengagement after refusal.

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
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (12)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
92% confidence
Finding

The description activates on very broad categories like '聊天', '浪漫', and '回应浪漫情况', which can overlap with ordinary social or writing requests and cause unintended routing of benign conversations into this persona/skill. Over-broad invocation increases the chance the skill will intervene outside its intended scope, potentially producing manipulative or sexualized guidance in contexts where the user did not explicitly ask for it.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
82% confidence
Finding

The description states the skill helps users communicate '与女生愉快交流', and subsequent sections repeatedly frame interactions as '她'. This hard-codes a gendered interaction model instead of offering inclusive language or letting the user specify the target audience, which is a natural-language policy concern.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
89% confidence
Finding

The quick-start trigger '当用户请求聊天/浪漫/撩妹建议时' is underspecified because '聊天' is extremely generic and could match a wide range of normal assistant use cases. In a skill-selection system, ambiguous triggers can misfire and apply persuasive relationship tactics to unrelated conversations, making the agent's behavior less predictable and potentially inappropriate.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
96% confidence
Finding

The file consistently assumes a heterosexual male user addressing a woman ('她') and presents only one gendered romantic framing without offering alternatives or user choice. In a broad conversational skill, this can misgender participants, exclude users with different orientations or identities, and steer outputs into biased or inappropriate assumptions in sensitive care scenarios.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
90% confidence
Finding

The entire skill is written only in Chinese and provides no indication that users may choose another language or locale. Under the stated policy, forcing a specific language without user 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.

Intent-Code Divergence

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The file's core principles say to stop when the other person is genuinely annoyed, but earlier examples encourage continued engagement after explicit rejection such as '我们不合适' or by reframing negative feedback into another advance. In a dating-advice skill, this inconsistency can normalize boundary-pushing behavior and lead users to persist after discomfort or rejection, increasing harassment risk.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
90% confidence
Finding

The file's natural-language instructions and examples are exclusively in Chinese, and there is no indication that the user can opt into another language or that the skill is intentionally limited to Chinese-speaking users. This can violate language/locale policy when a skill implicitly forces a specific language without user choice.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
91% confidence
Finding

This markdown file presents all guidance and examples exclusively in Chinese, and nowhere indicates that the user may choose another language or that the skill is intended only for a Chinese-language audience. Under the language/locale policy, forcing a specific language without user opt-in is a natural-language policy concern.

Content

No source excerpt is available for this finding.

Description-Behavior Mismatch

Low
Category
Not specified by scanner
Confidence
84% confidence
Finding

The manifest describes a skill focused on romantic chatting, flirtation, dating communication, and responses in romantic situations. Lines L078-L094 add unrelated generic internet joke comebacks about university, leaders, chess, and student evaluations, which are not clearly tied to dating or romantic communication use cases.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
83% confidence
Finding

The file presents all instructions and examples only in Chinese, and there is no indication that the user can choose another language or that the skill is intentionally limited to a Chinese-speaking context. Under the policy, forcing a specific language without user opt-in is a natural-language policy concern.

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 presents all instructions and examples exclusively in Chinese, and there is no natural-language indication that the skill is region-specific or that users can opt into another language. Under the policy rule, forcing a specific language without user choice can be a locale/language policy violation.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
80% confidence
Finding

This markdown file contains user-facing natural-language content exclusively in Chinese, with no indication that other languages are supported or that the language is user-selectable. Under the policy rule for language/locale constraints, forcing a specific language without opt-in can be a natural-language policy concern.

Content

No source excerpt is available for this finding.