ClawHub
Back to skill

Security audit

Muguozi1 Openclaw Context Budgeting

Security checks across malware telemetry and agentic risk

Overview

This skill is a context-management helper that writes checkpoint memory and may compact session context, which is disclosed and aligned with its purpose.

Install only if you want an agent to manage context by writing checkpoint summaries and compacting sessions. Review HOT_MEMORY.md before compaction, avoid saving secrets in summaries, preserve important raw data elsewhere, and treat the advertised tests and quality badges cautiously because the included test/example scripts are placeholders.

SkillSpector

By NVIDIA
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
Confidence
90% confidence
Finding
The documentation instructs the agent to update memory files and execute a cleanup/checkpoint script that performs 'physical cleanup' and clears raw data, but it does not warn about data loss, scope, rollback, or verification requirements. In an agentic environment, vague cleanup instructions can lead to deletion of needed state, corruption of memory artifacts, or unsafe automation against the wrong paths.

VirusTotal

58/58 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.