ClawHub
Back to skill

Security audit

BOOK BRAIN VISUAL READER – LYGO 3-Brain + Visual Left/Right Brain Helper

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed visual note-taking and indexing guide, with local files and web references that fit its stated purpose.

Install this only if you want the agent to maintain local notes, indexes, logs, and selected screenshots for visual verification. Review what folders and files it proposes before approving setup, especially if your workspace contains sensitive project material.

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
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Rogue AgentSelf-Modification, Session Persistence
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (2)

External Transmission

Medium
Category
Data Exfiltration
Content
External links:
- Clanker: https://clanker.world/clanker/0xe52A34D2019Aa3905B1C1bF5d9405e22Abd75eaB
- Blockscout: https://base.blockscout.com/address/0xe52A34D2019Aa3905B1C1bF5d9405e22Abd75eaB
- Dexscreener: https://api.dexscreener.com/latest/dex/search/?q=0xe52A34D2019Aa3905B1C1bF5d9405e22Abd75eaB

Related local files:
- reference/STARCORE_LAUNCH_RECEIPTS_2026-02-10.md
Confidence
50% confidence
Finding
Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.

Session Persistence

Medium
Category
Rogue Agent
Content
- Optionally topic-specific visual indexes (e.g. `reference/STARCORE_VISUALS.txt`).

4. **Log the setup**  
   - Add entry to `logs/book_brain_visual_setup.log` or `daily_health.md`.

5. **Respect all non-destructive rules**  
   - No overwrites.
Confidence
80% confidence
Finding
Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.

Static analysis

No suspicious patterns detected.