Back to skill

Security audit

**智能随机**:从8个维度、28个话题中均匀随机选择 - ⏰ **定时触发**:可配置的心跳机制,实现定时随机提问 - 🎨 **多维覆盖**:情绪、身体、思维、行动、关系、环境、反思、未来 - 🔧 **高度可定制**:支持话题库扩展、触发概率调整、个性化设置 - 📊 **使用统计**:详细的统计报告和图表分析 - 🔄 **上下文感知**:结合对话历史和个人档案

Security checks for vulnerabilities and agentic risk

Overview

This self-reflection skill is not malicious, but it should be reviewed because it can auto-prompt users and use or retain personal context and reflective answers without enough privacy detail.

Install only if you want scheduled reflective prompts and are comfortable with the skill using personal context and retaining answer history. Before enabling auto_load, heartbeat, backups, or personal-context features, confirm where data is stored, how long it is kept, and how to delete or disable it.

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)

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
88% confidence
Finding

The README advertises use of conversation history and personal profile for context awareness but does not disclose what data is accessed, how it is stored, or what user controls exist. In a self-reflection skill, these data sources are especially sensitive because they may contain intimate emotional, behavioral, or personal information, increasing privacy risk if users are unaware of the collection and use.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

The listed manual trigger phrases include ordinary conversational language such as '来个随机问题' and '我想被提问一下', which can overlap with normal user dialogue rather than an explicitly scoped command. In an agent skill context, broad natural-language triggers can cause unintended activation, producing unsolicited prompts and potentially interrupting or steering conversations without clear user intent.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
91% confidence
Finding

The description says the skill supports scheduled and event-based triggering but does not define guardrails such as which events are allowed, frequency limits, consent, or context checks. That ambiguity increases the risk of the skill activating at inappropriate times and prompting for introspective or sensitive information without a clear user expectation.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The manual invocation examples include ordinary conversational phrases such as '随机问我一个问题' and '我想被提问一下', which are broad enough to be matched during normal dialogue rather than an explicit command. In an agent environment, this can cause accidental activation, leading to unsolicited prompting and potential collection of personal reflections when the user did not intend to invoke the skill.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
97% confidence
Finding

The configuration and execution flow explicitly mention using personal context, remembering previous answers, and recording question history, but the skill description does not provide a clear privacy warning or explain retention and use of that data. Because the prompts solicit emotional, behavioral, and reflective responses, the stored history may contain sensitive personal information and create privacy risk if collected without informed consent.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
88% confidence
Finding

The manifest presents the skill name and description entirely in Chinese, with no indication that users can opt into another language or that the skill is intended only for a Chinese-speaking region. Under the policy criteria, forcing a specific language without user choice is a natural-language policy concern.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
84% confidence
Finding

The skill is configured for periodic activation via heartbeat, auto-loading, and random triggering with personal context enabled, but it lacks clear user-invocation constraints or explicit consent boundaries in the manifest. This can cause the agent to act unexpectedly, surface sensitive personal context at unintended times, or create persistent nuisance behavior that weakens user control.

Content

No source excerpt is available for this finding.

Skill Enumeration

Medium
Category
Agent Snooping
Confidence
80% confidence
Finding

Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.

Content

Scanner excerpt · example-openclaw.json (reported line 19)May include surrounding context.

json
"skills": {
    "random-question": {
      "enabled": true,
      "path": "skills/random-question/SKILL.md",
      "auto_load": true,
      "config": {
        "trigger_probability": 30,

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
84% confidence
Finding

All user-facing instructions, prompts, and invocation examples are Chinese-only, which effectively imposes a language constraint on users. The file does not offer multilingual support, opt-in language selection, or a justification that this is intentionally a Chinese-only regional skill.

Content

No source excerpt is available for this finding.