← Back to directory
claws-defender
OpenClaw runtime security plugin. It intercepts dangerous tool calls, blocks malicious memory writes, detects prompt injection and hazardous shell payloads, runs workspace security scans, and records security events to a local audit log.
Setup / get started
Start from the GitHub repository: source code and README for claws-defender.
Alternatives to claws-defender
Similar projects in this directory:
- Aquaman — Aquaman is a credential isolation proxy for OpenClaw Gateway that keeps API keys and channel tokens out of the agent…
- clawmoat — 🦀 Security moat for AI agents. Runtime protection against prompt injection, tool misuse, and data exfiltration.
- skill-bomb-dog-sniff — Security skill for OpenClaw - like a bomb-sniffing dog for skills. Detects malicious payloads before installation.
- openclaw-privacy-guardrail — OpenClaw plugin that blocks direct writes to public paths. Forces staging pipeline with mandatory privacy scrub.
- nulla-hive-mind — Runs a local-first agent runtime with memory, tools, and Hive task coordination for trusted multi-step work on your…
By Ch1nfoAdded 3/26/2026