ClawHub
Back to skill

Security audit

awareness-memory

Security checks for vulnerabilities and agentic risk

Overview

This memory skill is purpose-aligned, but its setup has enough persistent agent-configuration, local indexing, daemon, and telemetry impact that users should review it before installing.

Install only if you are comfortable with a memory layer that changes your agent rules/MCP config, runs a local daemon, stores cross-session project and conversation context, and may index local project documents. Review diffs after setup, prefer a dry run or manual setup where possible, avoid recording secrets or regulated data, and verify how to disable telemetry, delete stored memory, stop the daemon, and remove injected rules before using it on sensitive projects.

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 (2)

Missing User Warnings

Medium
Confidence
95% confidence
Finding
The skill instructs users to run a setup command that auto-detects IDEs, writes MCP configuration, and injects workflow rules into local files, but it does not clearly warn that local agent configuration and rule files will be modified automatically. This can lead users to make system and prompt-surface changes without informed consent, increasing the risk of unintended behavior, persistence, or trust in newly injected rules.

Missing User Warnings

Medium
Confidence
94% confidence
Finding
The skill promotes persistent cross-session memory, bulk ingestion, and backfilling of past conversations, but does not warn users that sensitive project data, prompts, credentials, or personal information may be stored locally for later retrieval. Without a privacy and data-handling warning, users may enable long-lived storage of confidential material without understanding retention, exposure, or sanitization risks.

Static analysis

No suspicious patterns detected.