ClawHub
Back to skill

Security audit

GEB Aesthetics

Security checks for vulnerabilities and agentic risk

Overview

This is a creative-writing/aesthetics framework skill with simple local project helper scripts and no evidence of hidden data access, persistence, or exfiltration.

This appears safe to install from a security perspective. Expect it to act as a creative framework, and run its project initialization helper only in the workspace where you want new creative project folders created.

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
  • Output HandlingUnvalidated Output Injection, Cross-Context Output, Unbounded Output
  • 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)

Unbounded Output

Medium
Category
Output Handling
Content
**Why GEB Matters for Creative AI:**

In an age where AI can generate infinite content, we face a crisis of meaning. Not everything that can be created should be created. GEB Aesthetics provides the **philosophical framework** to navigate this abundance—to create not more, but **better**; not faster, but **deeper**.

The three pillars of GEB guide our approach:
Confidence
80% confidence
Finding
Output size or generation rate is not bounded. Unbounded output enables denial-of-service through resource exhaustion, log flooding, or context-window stuffing.

Natural-Language Policy Violations

Low
Confidence
98% confidence
Finding
I reviewed the file for natural-language policy issues, especially any forced language or locale constraints. The README explicitly supports both Chinese and English, so there is no language/locale policy violation to report.

Static analysis

No suspicious patterns detected.