Back to skill

Security audit

Universal Occupation Adapter

Security checks for vulnerabilities and agentic risk

Overview

The skill is a coherent skill generator, but it encourages batch creation and automatic publication of new skills without clear review or confirmation safeguards.

Review generated skills before allowing this skill to write into your skills directory or publish to ClawHub. Avoid using auto_publish unless you have confirmed exactly what files will be created and uploaded, especially in workspaces containing private or organization-specific context.

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
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (7)

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The file uses Chinese-only headings and instructions such as "心跳触发" and "每日" with no indication that the skill is region-specific or that users may opt into another language. This creates a natural-language policy concern because it implicitly forces a specific language for operation and understanding.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
91% confidence
Finding

The README presents the skill's purpose, usage, and behavior only in Chinese, which effectively forces a specific language for users without any opt-in or alternative locale guidance. Under the policy, language constraints should either be optional for the user or clearly documented as a justified region-specific limitation.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

The skill explicitly advertises automatic generation, verification, and publication of newly created skills without a clear warning that this can create files and push artifacts externally. In an agent setting, this can lead to unintended workspace modification and accidental publication of sensitive or low-quality content if the user does not realize side effects are enabled.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The example enables auto_publish=True for batch generation to ClawHub without highlighting privacy, review, or confirmation requirements. This is risky because generated skills may contain sensitive workspace context, flawed content, or organization-specific data that could be published externally without adequate human review.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
90% confidence
Finding

This markdown file uses Chinese-only procedural headings and checklist items for the verification protocol, which can amount to a language/locale policy constraint. Because the document does not provide an opt-in, alternative language, or justification for restricting usage to Chinese, it may violate organizational language-choice expectations.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
86% confidence
Finding

The primary description text is in Chinese, and the document continues with mixed but predominantly Chinese instructions without indicating that users may choose another language. This can create a language policy issue when a skill effectively assumes a single language without opt-in or justification.

Content

No source excerpt is available for this finding.

Missing User Warnings

Low
Category
Not specified by scanner
Confidence
84% confidence
Finding

The installation instructions copy files into the user's local skills directory, modifying persistent agent configuration without an explicit warning. While common for installation docs, in a skill ecosystem this can still surprise users and lead to unintended activation of unreviewed capabilities.

Content

No source excerpt is available for this finding.