ClawHub
Back to skill

Security audit

Production Relations Refactor

Security checks for vulnerabilities and agentic risk

Overview

This is a Chinese-language advisory framework for organizational restructuring, with no executable code, persistence, credentials, or hidden data access.

Install only if you want a strongly opinionated Chinese-language framework for redesigning organizational workflows around AI-assisted execution. Treat its outputs as planning drafts, keep human review for staffing, governance, legal, safety, and compliance decisions, and be aware that broad trigger phrases may bring it into ordinary organization-design conversations.

A.I.G

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

SkillSpector

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 (2)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
92% confidence
Finding

The trigger list includes very broad phrases such as organizational restructuring, management flattening, and decision-rights restructuring, which can match ordinary business discussion and cause accidental skill invocation outside the user's intent. In this skill's context, accidental activation is more concerning because the skill strongly pushes a one-person, AI-mediated restructuring model that could steer high-impact organizational decisions without an explicit request for that framework.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
97% confidence
Finding

The skill description and all operating instructions are presented exclusively in Chinese, with no indication that the user may choose another language or that the locale restriction is intentional for a region-specific purpose. Under SQP-3, forcing a specific language without user opt-in is a natural-language policy concern.

Content

No source excerpt is available for this finding.