Self-improving Agent Memory Upgrade (SurrealDB)

• Analyzed: May 10, 2026, 6:54 AM
• Findings: 3
• Version: 2.3.0
• Reason codes:
  suspicious.dangerous_execsuspicious.env_credential_accesssuspicious.prompt_injection_instructions
• Engine: v2.4.23

Overview

Detected: suspicious.dangerous_exec, suspicious.env_credential_access, suspicious.prompt_injection_instructions

Findings (3)

critical

suspicious.dangerous_exec

• Location: openclaw-integration/gateway/memory.ts:273
• Finding: Shell command execution detected (child_process).

critical

suspicious.env_credential_access

• Location: openclaw-integration/gateway/memory.ts:32
• Finding: Environment variable access combined with network send.

warn

suspicious.prompt_injection_instructions

• Location: references/enhanced-loop-hook-agent-isolation.md:64
• Finding: Prompt-injection style instruction pattern detected.