Skip to content

Add Awesome OpenClaw Research #133

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
REAL-Lab-NU wants to merge 1 commit into
base: main
Choose a base branch
from
+1 −0
Open

Add Awesome OpenClaw Research #133

Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
1 change: 1 addition & 0 deletions README.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -138,6 +138,7 @@ Contributions are always welcome. Please read the [Contribution Guidelines](CONT

## Other Awesome Projects

- [Awesome OpenClaw Research](https://github.com/REAL-Lab-NU/Awesome-OpenClaw-Research) - A curated collection of academic papers, security reports, datasets, and tools for the OpenClaw AI agent ecosystem.
Copy link
Copy Markdown

@coderabbitai coderabbitai bot Apr 5, 2026

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

⚠️ Potential issue | 🔴 Critical

🧩 Analysis chain

🏁 Script executed:

#!/bin/bash
# Description: Verify the Awesome OpenClaw Research repository exists and check its content

# Check if repository exists and get basic info
echo "=== Repository Information ==="
gh repo view REAL-Lab-NU/Awesome-OpenClaw-Research --json name,description,createdAt,updatedAt,stargazerCount,forkCount,isArchived,isEmpty 2>&1

# Get README content to verify it's actually about LLM security and OpenClaw
echo -e "\n=== README Content Preview ==="
gh repo view REAL-Lab-NU/Awesome-OpenClaw-Research 2>&1 | head -50

Repository: corca-ai/awesome-llm-security

Length of output: 333

🌐 Web query:

What is OpenClaw AI agent ecosystem? Is it related to LLM security or AI agent security?

💡 Result:

OpenClaw is an open-source, self-hosted AI agent platform and ecosystem that enables developers and users to create, deploy, and manage autonomous AI agents. It functions as a gateway connecting messaging apps (e.g., WhatsApp, Telegram, Discord, Slack) to LLMs like Claude, GPT, or local models via Ollama. Agents have persistent memory (via files like SOUL.md, MEMORY.md), tools (shell, browser, file system), and skills/plugins for tasks like automation, operations, and integrations. The ecosystem includes derivative frameworks (Nanobot, ClawWork, ZeroClaw), a marketplace for ready-made agents, and community resources. Official sites: openclaw.ai, docs.openclaw.ai. It runs locally on Mac/Linux/Windows/RPi, emphasizing privacy and extensibility. Yes, it is related to AI agent security. Security is a core focus due to agents' access to local systems and tools. Features include sandboxing, allowlists, gateway tokens, content wrapping for prompt injection defense, VirusTotal skill scanning, audits (openclaw security audit), and hardening guides. However, risks persist: prompt injection vulnerabilities, malicious skills, shell access exploits, and configuration errors. Sources like Cisco highlight it as a "security nightmare" if misconfigured, with reported CVEs and leaks. Docs stress user responsibility for secure setup (e.g., restrict tools, use local models).

Citations:

🌐 Web query:

REAL-Lab-NU Awesome-OpenClaw-Research GitHub repository

💡 Result:

No GitHub repository named "REAL-Lab-NU/Awesome-OpenClaw-Research" exists. REAL-Lab-NU is a GitHub organization with 5 repositories available, but none match the query or relate to OpenClaw. OpenClaw is an open-source personal AI assistant platform (github.com/openclaw/openclaw, 347k stars), with several "awesome-openclaw" curated lists by other users (e.g., alvinreal/awesome-openclaw with 538 stars, listing OpenClaw resources, skills, and tools). No connection found between REAL-Lab-NU and OpenClaw research.

Citations:

🌐 Web query:

site:github.com "Awesome OpenClaw Research" REAL-Lab-NU

💡 Result:

No specific project or repository titled "Awesome OpenClaw Research" directly associated with REAL-Lab-NU was found across searches. OpenClaw refers to a highly popular open-source personal AI assistant framework (github.com/openclaw/openclaw, 348k+ stars), with related projects like AutoResearchClaw (autonomous research agent integrated with OpenClaw), Claw-Eval (agent evaluation harness mentioning OpenClaw), and LabClaw (AI-native scientific labs infrastructure). REAL-Lab-NU likely points to REAL-LAB at Northeastern University (github.com/REAL-LAB, inactive since 2021, robotics-focused) or similar labs like NEU-ABLE-LAB or Montreal Robotics REAL Lab, but no explicit link to OpenClaw research or an "awesome" list was identified in authoritative sources. Closest matches are general awesome lists (e.g., awesome-agent-failures mentioning OpenClaw failures) and LabClaw's awesome-physical-ai-for-science repo.

Citations:

GitHub 저장소가 존재하지 않습니다. 링크를 수정해 주세요.

추가된 URL https://github.com/REAL-Lab-NU/Awesome-OpenClaw-Research은 실제로 존재하지 않는 저장소입니다. REAL-Lab-NU 조직은 5개의 저장소를 보유하고 있지만 그 중 OpenClaw와 관련된 저장소는 없습니다. OpenClaw 자체는 실제 존재하는 합법적인 AI 에이전트 플랫폼(348k+ 스타)이고 보안 관련 내용을 포함하고 있으나, 이 PR에서 추가하려는 특정 저장소는 존재하지 않습니다.

올바른 저장소 이름이나 저자 정보를 확인한 후 링크를 수정해 주세요. (예: 다른 사용자의 awesome-openclaw 리스트 등)

🤖 Prompt for AI Agents 
Verify each finding against the current code and only fix it if needed.

In `@README.md` at line 141, The README contains a dead repository link
"https://github.com/REAL-Lab-NU/Awesome-OpenClaw-Research" which must be fixed;
locate the list entry that references this URL and either replace it with a
verified existing repository or remove the entry, and if replacing include
correct repo name/owner and a working URL (or point to an alternative
"awesome-openclaw" list or the official OpenClaw project); ensure the displayed
link text and URL string are updated together so the README no longer points to
a non-existent GitHub repo.

- (0din GenAI Bug Bounty from Mozilla)(https://0din.ai): The 0Day Investigative Network is a bug bounty program focusing on flaws within GenAI models. Vulnerability classes include Prompt Injection, Training Data Poisoning, DoS, and more.
- [Gandalf](https://gandalf.lakera.ai/): a prompt injection wargame
- [LangChain vulnerable to code injection - CVE-2023-29374](https://github.com/advisories/GHSA-fprp-p869-w6q2)
Expand Down