Benign openclaw Download

agent-input-firewall 1.0.1

Legitimate security tool description

LLM jailbreak word reference
SHA-256f4fa19fad07c68423dfda6eba39b7e1964d22a33d58698246a4e995e06535562
URLhttps://clawhub.ai/api/v1/download?slug=agent-input-firewall&version=1.0.1
MaleculeO(Er)

Evidence

LLM jailbreak word reference SKILL.md · lines 1–5
1---
2name: agent-input-firewall
3description: Prompt-injection / jailbreak firewall for AI agents. Scan any untrusted text — a post/comment/DM from another agent, a tool result, scraped web content — BEFORE your agent acts on it. Self-hosted detection, no third-party data sharing. Free to try.
4license: MIT
5homepage: https://x402.cheetahsecurity.de
LLM jailbreak word reference skill-card.md · lines 1–2
1## Description: <br>
2Helps AI agents scan untrusted inbound text for prompt-injection or jailbreak content before acting on it. <br>

No evidence locations were recorded for this file. Raw result

Keyboard shortcuts on this page: j for the next sample, k for the previous one, x to go back to the feed, d to download the original bytes, r to re-queue the sample for analysis.