rce.
Everything we've published on rce across guides, agents, hardware reviews and glossary entries: 8 entries in total.
Guides (2)
- OpenClaw security crisis 2026: what you need to knowAI Agents · 2026-10-27
CVE-2026-25253 let one crafted link take over an OpenClaw gateway, and The Register counted more than 135,000 instances reachable from the internet. What happened, what was exposed, and what to do.
- Langflow, n8n, LiteLLM: the AI builders on CISA KEV in 2026AI Agents · 2026-10-13
CISA added nine Langflow, n8n and LiteLLM CVEs to its exploited list in 2026. The versions to run, the three bug patterns, and what to lock down.
Agents (2)
- Hermes Agent
Agent from Nous Research (MIT, Python). Runs shell commands on the host by default, with an approval step for dangerous ones; Docker and cloud sandboxes are options. Works with many LLM providers.
- IronClaw
Rust agent from NEAR AI, MIT or Apache-2.0. Untrusted tools run in a WebAssembly sandbox with declared capabilities, and secrets are injected outside them.
Glossary (4)
- OpenClaw :Open-source AI agent started by Peter Steinberger in late 2025 as Clawdbot, renamed Moltbot, then OpenClaw.
- Hermes Agent :Open-source (MIT) AI agent from Nous Research. Multi-LLM; runs commands on the host behind approvals unless you choose a sandbox backend.
- MCP (Model Context Protocol) :Open protocol for connecting language models to tools and data sources over JSON-RPC.
- RCE (Remote Code Execution) :Vulnerability class where an attacker can execute arbitrary code on a target system over a network.