From 13c35757dac97863c0057d6f4658a0cd7d6caa84 Mon Sep 17 00:00:00 2001 From: awdemos Date: Wed, 15 Jul 2026 19:08:20 -0500 Subject: [PATCH] Add Redcells Ultraworked with [Sisyphus](https://github.com/code-yeongyu/oh-my-openagent) Co-authored-by: Sisyphus --- README.md | 1 + 1 file changed, 1 insertion(+) diff --git a/README.md b/README.md index d6c0bf5..32fff11 100644 --- a/README.md +++ b/README.md @@ -346,6 +346,7 @@ AI agents increasingly use external tools, plugins, and skills to interact with | Tool | Description | Link | |------|-------------|------| +| **[Redcells](https://github.com/awdemos/redcell)** | Automated adversarial testing platform for the LLMs you own or control; also supports agentic red teaming of tool-calling models. | [![GitHub](https://img.shields.io/github/stars/awdemos/redcell)](https://github.com/awdemos/redcell) | | **[Agent Memory Guard](https://github.com/OWASP/www-project-agent-memory-guard)** | OWASP reference implementation for ASI06 (Memory Poisoning): runtime defense that screens every agent memory read/write through detectors + a declarative policy, with source-class provenance, forensic SecurityEvents, and snapshot rollback. LangChain/OpenAI-Agents/AutoGen/CrewAI/mem0 integrations | [![GitHub](https://img.shields.io/github/stars/OWASP/www-project-agent-memory-guard)](https://github.com/OWASP/www-project-agent-memory-guard) | | **[Bounty Sieve](https://github.com/junbuilds96/bounty-sieve)** | Offline-by-default bounty intake guardrail for coding agents: read-only GitHub issue/URL-list import, deterministic triage, local decision briefs, and human approval gates | [![GitHub](https://img.shields.io/github/stars/junbuilds96/bounty-sieve)](https://github.com/junbuilds96/bounty-sieve) | | **[SkillGuard](https://github.com/LLMSecurity/skillguard)** | LLM-native agent skill security auditor (OWASP Agentic + MITRE ATLAS) | [![GitHub](https://img.shields.io/github/stars/LLMSecurity/skillguard)](https://github.com/LLMSecurity/skillguard) |