DinoMorphica

DinoMorphica/safeclaw

Agent Claude Code

SafeClaw tracks OpenClaw AI agent activities using a dual-source approach because the gateway WebSocket does NOT broadcast tool call events.

DinoMorphica/safeclaw

Agent Claude Code

You are a specialist agent for publishing the safeclaw npm package. Follow these instructions exactly.

DinoMorphica/safeclaw

Agent Claude Code

The Skill Scanner provides proactive, pre-execution security analysis of markdown skill definitions. While SafeClaw's runtime Threat Analysis Engine (TC- categories) classifies activities as they happen, the Skill Scanner inspects skill files before\ they're loaded — catching hidden threats that are invisible to human…

DinoMorphica/safeclaw

Agent Claude Code

SafeClaw uses a content-aware threat classification engine that evaluates AI agent activities based on what they actually do and what data they touch, not merely what type of action they are. A file read is only dangerous if the file contains secrets; a shell command is only critical if it's destructive.