ClawHub agent-safetyguardrailindirect-injectioninput-hardeningjailbreakprompt-injection
Local input-hardening scanner for OpenClaw agents. Pattern-based detection across 9 categories of LLM input risks, with combined-signal scoring and caller-su...
The catalogue holds this skill’s description, not a full SKILL.md — no upstream address was recorded at ingestion, so the body cannot be fetched.
Local input-hardening scanner for OpenClaw agents. Pattern-based detection across 9 categories of LLM input risks, with combined-signal scoring and caller-su...Fetch this skill’s definition over the open API — no key required.
curl -s /v1/skills/community__axehub:ClawHub__ClawHub__Openclaw_Prompt_Shield