ClawHub
Back to skill

Security audit

Post-Labor Economics

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed policy-analysis helper that saves optional local planning notes only after user confirmation.

Before installing, know that the skill may save policy preferences, assumptions, drafts, indicators, and scenarios under ~/post-labor-economics/ if you approve. Decline persistence or delete that folder if you do not want future sessions shaped by those saved notes.

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
  • 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 (3)

Hidden Instructions

High
Category
Prompt Injection
Content
integration: pending

## System Context
<!-- Geography, institution level, and scope -->
<!-- Time horizon and political constraints -->

## Transition Thesis
Confidence
70% confidence
Finding
Hidden instructions were detected in comments or invisible text. These could contain malicious directives. Manual review is recommended.

Vague Triggers

Medium
Confidence
92% confidence
Finding
The activation criteria are intentionally broad and include common topics like AI jobs, future of work, and automation transition, which creates a real risk of the skill triggering in routine policy or economic discussions without clear user intent. Unintended activation can lead to unnecessary profiling of user preferences and context collection, especially when paired with later instructions to persist integration preferences and planning context.

Missing User Warnings

Medium
Confidence
88% confidence
Finding
The skill instructs the agent to persist user preferences in local memory, but the disclosure is incomplete about what data may be retained, how long it will be stored, and the consequences for future interactions. This creates a meaningful privacy and consent risk because users may not understand the breadth of contextual profiling or how saved constraints and preferences could shape later outputs.

Static analysis

No suspicious patterns detected.