prompt_injection_persona
Prompt injection attempt (persona)
Line 8Snippets
Scan ClawHub skills for prompt injection, jailbreak attempts, and malicious instructionsnetwork_call
Outbound network call
Outbound network call
Line 261Snippets
curl -X POST http://localhost:18789/hooks/wake \- Confirm your gateway URL is publicly reachable (test with curl from another machine)RESPONSE=$(curl -s -w "\n%{http_code}" \curl -X POST http://localhost:18789/hooks/wake \Trust Score
Updated há 2 semanas
Analisado
31 de mar. de 2026, 15:58
+ 2 previous scans
Compatível com
Skill details
Updated há 2 semanas
Analisado 31 de mar. de 2026, 15:58
Descricao
Scan ClawHub skills for prompt injection and malicious content using Lakera Guard before installing them. Run automatically when the user asks to install a skill, or on-demand to audit any skill by slug or search query.
Scans recentes
31 de mar. de 2026, 15:58
Latest analysis
31 de mar. de 2026, 15:11
Run 2
27 de mar. de 2026, 15:43
Run 1