ClawHub
Back to skill

Security audit

Dream Maker

Security checks for vulnerabilities and agentic risk

Overview

This skill is a creative dream generator that only asks the agent to read and write scoped dream files, with no evidence of hidden code, network use, credentials, or destructive behavior.

Install this only if you are comfortable with the agent creating and updating files under memory/dreams. Review that folder occasionally if you do not want generated dream text to accumulate, and ask the agent before use if you want confirmation before each save.

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
  • 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
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (1)

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
96% confidence
Finding

The skill explicitly instructs the agent to save generated content into memory/dreams/YYYY-MM-DD-HHMM.md and to update a tracking log, but it does not require user awareness or confirmation before modifying persistent storage. In an agent environment, silent writes can create unwanted state changes, overwrite user expectations about memory usage, and normalize unauthorized file modification even if the content itself is non-executable.

Content

No source excerpt is available for this finding.