ClawHub
Back to skill

Security audit

[Nyx Archive] Bound Memory

Security checks for vulnerabilities and agentic risk

Overview

This is an instruction-only memory skill whose local read/write behavior is disclosed and aligned with its purpose, but users should treat the persisted memory files as private records.

Install only if you want the agent to maintain persistent local memory. Keep the named memory files in a private, user-controlled directory, review them periodically, and avoid storing secrets, credentials, or sensitive personal details unless you intentionally want them preserved.

SkillSpector

Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • 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
93% confidence
Finding
The skill explicitly instructs the agent to update multiple persistent memory files after every meaningful exchange, but it does not require user consent, confirmation, or any guardrails around when writes are appropriate. In an agent environment with filesystem access, this can cause silent persistence of conversation content, leakage of sensitive data into long-lived files, and unintended cross-session behavioral drift.

Static analysis

No suspicious patterns detected.