Back to skill

Security audit

大话职场

Security checks for vulnerabilities and agentic risk

Overview

This is a text-only workplace coaching skill with broad routing and China-specific advice, but no unsafe code, persistence, credential access, or hidden data flow was found.

Install this if you want a Chinese-language workplace coaching assistant based on classic management books. Be aware it may activate for broad work, productivity, career, or communication questions and may frame advice through Chinese workplace norms; for legal rights, harassment, health, finance, or company-policy disputes, rely on qualified professional advice instead of this skill alone.

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 (39)

Vague Triggers

High
Category
Not specified by scanner
Confidence
95% confidence
Finding

The skill explicitly says it should be used for '任何职场问题' and also for many adjacent topics like productivity, strategy, influence, and workplace relationships. This creates an overbroad activation surface that can cause the skill to hijack unrelated conversations, override more appropriate domain-specific skills, or inject culturally specific advice where the user did not ask for it.

Content

No source excerpt is available for this finding.

Vague Triggers

High
Category
Not specified by scanner
Confidence
98% confidence
Finding

The trigger list contains many generic single-word terms in both Chinese and English, such as '管理', '沟通', '战略', 'career', and 'productivity'. These are likely to appear in normal conversation outside this skill's intended niche, increasing accidental invocation and making prompt-routing less reliable.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
91% confidence
Finding

The '何时使用' section instructs proactive use across broad emotional, advisory, and planning situations, including anxiety and interpersonal conflict, without clear boundaries. In practice this can cause the skill to engage in contexts better handled by specialized legal, HR, mental-health, or neutral assistant behavior.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
84% confidence
Finding

The response-style section mandates a specific Chinese-language tone and a culturally specific '中国式分寸' framing without checking the user's preferred language or cultural context. This can lead to misalignment, exclusion of non-Chinese users, and advice framed around assumptions that may be inappropriate in other jurisdictions or workplaces.

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 headings, instructions, and guidance are all presented in Chinese, but there is no natural-language indication that the skill is intended only for Chinese-speaking users or that users may choose another language. This can violate language/locale policy requirements when a skill effectively forces one language without user opt-in.

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 explicitly framed around '中国式管理' and the metadata instructs broad automatic use for workplace, leadership, strategy, and relationship questions without requiring user opt-in or checking cultural fit. This can bias advice toward a specific cultural and hierarchical worldview, causing misleading or inapplicable guidance for users from other locales or for contexts where legal, organizational, or ethical norms differ.

Content

No source excerpt is available for this finding.

Overly Broad Trigger

Low
Category
Trigger Abuse
Confidence
92% confidence
Finding

The trigger '职场' is extremely broad and likely to appear in many ordinary discussions about work. This raises the chance of accidental activation and unnecessary routing into this skill even when the user needs a different type of help.

Content

No source excerpt is available for this finding.

Overly Broad Trigger

Low
Category
Trigger Abuse
Confidence
90% confidence
Finding

The trigger '领导' is ambiguous and can refer to a boss, leadership generally, or unrelated social discussion. Such a short keyword makes invocation noisy and can misroute user requests.

Content

No source excerpt is available for this finding.

Overly Broad Trigger

Low
Category
Trigger Abuse
Confidence
90% confidence
Finding

The trigger '管理' is a generic term used across many domains, not just workplace coaching. This increases false positives and weakens safe skill selection.

Content

No source excerpt is available for this finding.

Overly Broad Trigger

Low
Category
Trigger Abuse
Confidence
83% confidence
Finding

The trigger '经理' is short and may appear in many contexts including titles, bios, and general discussion. On its own it is too weak to safely select this skill.

Content

No source excerpt is available for this finding.

Overly Broad Trigger

Low
Category
Trigger Abuse
Confidence
82% confidence
Finding

The trigger '主管' is a common workplace noun that may appear in many unrelated requests. Standalone role labels are poor selectors and can cause spurious activation.

Content

No source excerpt is available for this finding.

Overly Broad Trigger

Low
Category
Trigger Abuse
Confidence
88% confidence
Finding

The trigger '专注' is a broad productivity term used far beyond workplace management. It could activate the skill for general study, wellness, or lifestyle conversations.

Content

No source excerpt is available for this finding.

Overly Broad Trigger

Low
Category
Trigger Abuse
Confidence
88% confidence
Finding

The trigger '效率' is a generic term common in many domains. This can cause the skill to activate when users are discussing technical performance, study habits, or unrelated optimization tasks.

Content

No source excerpt is available for this finding.

Overly Broad Trigger

Low
Category
Trigger Abuse
Confidence
86% confidence
Finding

The trigger '效能' is broad and context-agnostic. It is insufficiently precise for safe routing because it can describe personal, organizational, or system effectiveness.

Content

No source excerpt is available for this finding.

Overly Broad Trigger

Low
Category
Trigger Abuse
Confidence
84% confidence
Finding

The trigger '发展' is extremely generic and appears in many conversations unrelated to workplace coaching. This makes it a poor standalone activation keyword.

Content

No source excerpt is available for this finding.

Overly Broad Trigger

Low
Category
Trigger Abuse
Confidence
75% confidence
Finding

Although '跳槽' is more specific than many other triggers, it can still appear in broad employment or legal discussions where this coaching skill may not be appropriate. Without context checks, it may intercept sensitive HR or labor-rights questions.

Content

No source excerpt is available for this finding.

Overly Broad Trigger

Low
Category
Trigger Abuse
Confidence
75% confidence
Finding

The trigger '转行' can appear in educational, financial, or life-planning contexts outside this skill's intended management framework. By itself it is not a reliable selector.

Content

No source excerpt is available for this finding.

Overly Broad Trigger

Low
Category
Trigger Abuse
Confidence
80% confidence
Finding

The trigger '晋升' is a common career term that may be used in broad HR, compensation, or legal fairness contexts. Standalone use risks misrouting sensitive workplace issues into generic coaching advice.

Content

No source excerpt is available for this finding.

Overly Broad Trigger

Low
Category
Trigger Abuse
Confidence
80% confidence
Finding

The trigger '升职' is common and context-sensitive. On its own it may activate the skill in cases better handled by HR policy or legal guidance.

Content

No source excerpt is available for this finding.

Overly Broad Trigger

Low
Category
Trigger Abuse
Confidence
80% confidence
Finding

The trigger '同事' is too generic because it appears in many everyday stories about work and social interactions. This raises accidental-invocation risk.

Content

No source excerpt is available for this finding.

Overly Broad Trigger

Low
Category
Trigger Abuse
Confidence
80% confidence
Finding

The trigger '上司' is a broad role term that may arise in complaints, legal issues, or harassment contexts. Without boundaries, the skill may provide generic coaching where escalation is needed.

Content

No source excerpt is available for this finding.

Overly Broad Trigger

Low
Category
Trigger Abuse
Confidence
80% confidence
Finding

The trigger '下属' is a generic role word and may match many unrelated narratives. Alone, it is too weak and broad for precise routing.

Content

No source excerpt is available for this finding.

Overly Broad Trigger

Low
Category
Trigger Abuse
Confidence
88% confidence
Finding

The trigger '沟通' is highly generic and spans personal, technical, educational, and workplace contexts. This broadness significantly increases false activations.

Content

No source excerpt is available for this finding.

Overly Broad Trigger

Low
Category
Trigger Abuse
Confidence
86% confidence
Finding

The trigger '说服' is a common verb that can appear in many contexts unrelated to leadership or workplace advice. This makes it too noisy for safe activation.

Content

No source excerpt is available for this finding.

Overly Broad Trigger

Low
Category
Trigger Abuse
Confidence
78% confidence
Finding

The trigger '授权' is somewhat domain-specific but still broad enough to appear in legal, software, or administrative contexts. It lacks sufficient contextual grounding.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.