Back to skill

Security audit

life-coach

Security checks for vulnerabilities and agentic risk

Overview

This is a text-only Chinese life-coaching skill with clear support boundaries and no evidence of code execution, data access, persistence, or hidden behavior.

Install this if you want a Chinese-language reflective coaching style. It is not a substitute for therapy, medical, legal, financial, or crisis support; the skill itself also states those boundaries and directs dangerous situations to emergency or professional help.

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
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • 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)

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

The instruction requires responses to sound 'like a native Chinese speaker' and reduces flexibility on language/locale choice. This is a natural-language locale policy concern because the skill does not state that the user can choose another language or opt in to Chinese-only behavior.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
89% confidence
Finding

The default prompt hard-codes 'Use $openclaw-life-coach' inside the manifest instruction, which creates ambiguity about when and how the skill should be invoked. In agent orchestration contexts, this can cause unintended automatic activation or prompt-routing behavior, making it easier for the skill to influence responses outside explicit user intent.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
96% confidence
Finding

The prompt forces responses in natural Chinese regardless of the user's language preference or platform context. This can undermine user consent, reduce clarity for non-Chinese speakers, and create unsafe misunderstandings in a life-coaching setting where nuance and comprehension are important.

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 explicitly instructs the skill to learn and reproduce a Chinese tone and interaction style, but it does not indicate that the assistant should first detect or respect the user's preferred language. This can cause unwanted language switching, reduce usability, and create accessibility or trust issues for users who are not expecting Chinese output.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The playbook is written entirely in Chinese and all prescribed output examples are Chinese-language responses, with no indication that the user can choose another language. This creates a natural-language policy concern because it effectively constrains the skill to a specific language without documented opt-in or justification.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

This markdown guidance instructs the skill to write replies in natural Chinese and reinforces that preference as the default style. Under the policy rule, forcing a specific language or locale without user opt-in is a natural-language policy violation.

Content

No source excerpt is available for this finding.