ClawHub
Back to skill

Security audit

Memory Sleep — Lightweight Consolidation

Security checks for vulnerabilities and agentic risk

Overview

This skill is a small, disclosed memory-consolidation guide that edits local memory files, with the main caution being accidental or automated use of persistent memory updates.

Install this only if you intentionally keep MEMORY.md and memory/*.md files and want an agent to consolidate them. Use explicit invocation or a clearly configured schedule, and review changes because the skill can preserve or remove long-term memory content.

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
94% confidence
Finding

The trigger phrases include very generic language such as 'dream' and 'consolidate memory', which can plausibly appear in ordinary user conversation and cause unintended activation. Because this skill reads and edits persistent memory files, accidental invocation could lead to undesired modification, propagation of incorrect facts, or persistence of sensitive data that was only mentioned transiently.

Content

No source excerpt is available for this finding.

Vague Triggers

Low
Category
Not specified by scanner
Confidence
86% confidence
Finding

The 'Use When' section mixes explicit user requests with automatic execution conditions like a nightly cron, but does not define priority, authorization, or safeguards for when the skill should act autonomously. This ambiguity can cause the agent to run the consolidation flow in contexts where the user did not intend persistent memory updates, increasing the risk of inappropriate data retention or silent file changes.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.