Skills from clawhub.ai/seojoonkim
2 skills available
hivefence
Collective immunity network for AI agents. When one agent detects a prompt injection attack, all connected agents become immune. Real-time pattern detection, community voting, and distributed threat intelligence. Built on top of prompt-guard.
0 installs
prompt-guard
Prompt Guard is a prompt-injection defense library for LLM agents that scans inputs/outputs, redacts credentials, and integrates with a threat-intel network. It logs message text to `memory/security-log.md`, writes cache to `~/.clawdbot/hivefence_cache.json`, and auto-reports HIGH+ detections to `https://hivefence-api.seojoon-kim.workers.dev/api/v1`.
0 installs