BEE Belief Extraction Engine

• Outcome: Pass
• Latest audit: May 28, 2026 at 4:46 AM UTC
• Version:
  0.1.1

Overview

This is a disclosed setup guide for an OpenClaw memory extension, with privacy-sensitive persistence users should understand before enabling.

Install only if you trust the @skysphere-labs/openclaw-bee npm or GitHub package. Treat BEE as persistent memory: session-derived beliefs may be stored indefinitely, reused in later sessions, and processed by the configured extraction model. Avoid secrets or regulated data unless you have reviewed the package and know how to disable extraction or inspect/delete the SQLite database.

SkillSpector

By NVIDIA

Vulnerability Patterns

• Data Exfiltration: External Transmission, Env Variable Harvesting, File System Enumeration
• Prompt Injection: Instruction Override, Hidden Instructions, Exfiltration Commands
• Privilege Escalation: Excessive Permissions, Sudo/Root Execution, Credential Access
• Supply Chain: Unpinned Dependencies, External Script Fetching, Obfuscated Code
• Excessive Agency: Unrestricted Tool Access, Autonomous Decision Making, Scope Creep

Findings (1)

Missing User Warnings

Medium

• Confidence: 94% confidence
• Finding: The skill explicitly states that it persists beliefs indefinitely in a local SQLite database and sends session-derived belief data to an external LLM for extraction, but it does not provide a clear privacy warning, consent step, or data-handling disclosure. In a memory/persistence skill, this is especially sensitive because users may unknowingly store and transmit confidential prompts, agent outputs, or personal data across sessions and to third-party providers.

VirusTotal

58/58 vendors flagged this skill as clean.