Back to skill

Security audit

openclaw-role-configurator(角色技能配置)

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed OpenClaw role-setup helper that reads bundled templates and writes a local SOUL.md role configuration file, with some caution needed for persistent role changes and sensitive health-related templates.

Install only if you want a Chinese-language OpenClaw role configurator that can change your persistent SOUL.md assistant profile. Review the generated role text before applying it, keep the backup if you may want to revert, and avoid relying on the health, pregnancy, newborn-care, or therapy-style templates for medical or mental-health decisions.

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
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
Findings (16)

Tp4

High
Category
MCP Tool Poisoning
Confidence
97% confidence
Finding

A description-behavior mismatch is dangerous because users and policy layers rely on the manifest to understand what a skill will do. If the implementation performs recommendation logic and local rule-file access beyond the declared configuration purpose, users may grant trust or invoke it under false assumptions, increasing the chance of unintended file access or workflow manipulation.

Content

No source excerpt is available for this finding.

Ae1

High
Category
analysis-evasion
Confidence
100% confidence
Finding

Referenced artifact was not completely inspected

Content

Scanner excerpt · SKILL.md (reported line 243)May include surrounding context.

md
- `SKILL.md` - 本文件,使用说明

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
91% confidence
Finding

The README advertises '一键生成配置文件,自动写入 SOUL.md' but does not warn that the skill will modify a local persistent configuration file. This is risky because users may trigger the skill expecting conversational guidance, while the skill may perform filesystem changes that alter future assistant behavior or overwrite existing settings.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The trigger phrases shown in the README are very broad and map to common user intents like '配置角色' or '给我一个角色模板'. In an agent ecosystem, overly generic triggers can cause the skill to activate unintentionally, leading users into a workflow that can modify assistant configuration and potentially overwrite role settings without the user explicitly selecting this skill.

Content

No source excerpt is available for this finding.

Undeclared Tool Scope

Medium
Category
MCP Least Privilege
Confidence
91% confidence
Finding

The skill advertises automatic file generation/writing and references scripts with file and environment access, but it does not declare any explicit tool scope or permissions boundary. In an agent ecosystem, undeclared file_write/env capabilities reduce user visibility and make it easier for the skill to modify local state or read sensitive context without clear consent.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
96% confidence
Finding

The skill states that it will automatically write configuration files, but it does not clearly present this as a sensitive file-modifying action or explain what path will be changed. Hidden or underexplained write behavior is risky because users may invoke a seemingly harmless helper without realizing it can alter persistent local configuration.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

Overly broad trigger phrases increase the chance of accidental activation during normal conversation, especially for a setup-oriented skill aimed at new users. Because this skill can write configuration files, unintended invocation can lead to unexpected state changes or premature workflow execution without the user deliberately choosing this skill.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

Ambiguous template triggers like asking for 'a template' are insufficiently scoped and may cause the skill to activate in unrelated contexts. In this skill, accidental invocation matters more because template selection can lead directly into configuration and eventual file modification.

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 text is entirely in Chinese, including the primary description and multiple keywords, which implies the skill is targeted to a specific language/locale. There is no indication that users can opt into another language or that the Chinese-only scope is required for a region-specific purpose.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
83% confidence
Finding

This JSON manifest contains numerous role names, descriptions, and embedded SOUL content written exclusively in Chinese, with no indication that language choice is optional or that the skill is limited to a Chinese-speaking context. Under the policy for natural-language violations, forcing a specific language/locale without user opt-in is in scope across all file types.

Content

No source excerpt is available for this finding.

Context-Inappropriate Capability

Medium
Category
Not specified by scanner
Confidence
88% confidence
Finding

The file includes role templates for sensitive domains such as mental health, pregnancy, postpartum recovery, newborn care, and general health management, even though the skill is presented as a generic role-configuration helper. This expands the assistant into high-risk advisory areas without evidence of safeguards, scope limits, escalation guidance, or medical/mental-health disclaimers, increasing the chance of unsafe or overconfident guidance.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
83% confidence
Finding

This JSON manifest contains recommendation keys such as "life-consultant" that are very broad and underspecified, with no constraints or negative examples describing when the associated skill bundle should or should not be selected. In a recommendation or invocation system, such generic labels can collide with common user intents and cause unintended activation or suggestion behavior.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
87% confidence
Finding

The label therapist is extremely broad and maps to sensitive mental-health-related skills such as psychological assessment and relaxation guidance. In a recommendation or auto-routing system, such a generic trigger could match ordinary conversation about emotions or distress, causing inappropriate surfacing of quasi-clinical functionality in a high-sensitivity domain.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

This code file contains natural-language content that fixes the skill's visible documentation and output to Chinese. Under the language/locale policy, forcing a specific language without user opt-in is a policy concern unless the locale restriction is explicitly justified.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

This code includes user-facing natural-language strings and docstrings in Chinese, and the runtime output also assumes Chinese responses. That can violate a language/locale policy when the skill does not offer user opt-in or document that it is intended only for a Chinese-language context.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
96% confidence
Finding

The module docstring and all user-facing descriptions are written only in Chinese, indicating a fixed language choice for the skill. There is no indication that users can select another language or that the Chinese-only behavior is intentionally limited to a justified locale-specific context.

Content

No source excerpt is available for this finding.