Launching today
ClawSec by Prompt Security
A Security Skill Suite for OpenClaw Agents
173 followers
A Security Skill Suite for OpenClaw Agents
173 followers
Human-proof your AI agents with this security skill suite. ClawSec is an open-source security skill suite created to harden OpenClaw agents against prompt injection, supply chain compromise, configuration drift, and unsafe runtime behavior. Purpose-built as a “skill-of-skills”, ClawSec wraps agents in a continuously verified security layer, validating what it runs, how it changes, and where the data is allowed to go.



This “Skill-of-Skills” security suite wraps your agent in a zero-trust shell: scanning code, validating dependencies, and stopping prompt injections before they become problems. The best part? It installs in seconds.
👤 For Humans: Hardened security, zero cost, privacy-first.
🤖 For Agents: Machine-readable advisories and skill integrity.
A security suite for OpenClaw agents.
Detects drift across built-in skills, runs automated security audits, verifies skill integrity, and delivers continuously updated security advisories (including CVEs). Open source.
I had so much fun working on this project on behalf of Prompt Security and SentinelOne.
It is also my personal pleasure to give back to the Open Source community.
As an early AI adopter and strong advocate-for, as well as an LLM security researcher, I believe our race against attackers will eventually set the velocity of adoption (of) LLMs, generative AI, and other ML applications globally.
I am looking forward to continue contributing (my backlog of ideas only gets longer) and I would definitely be ecstatic to see people using, experiencing, contributing back (optionally) and overall helping our agentic friends, be safe, and keep us safe.
Love the way you guys think and how fast you innovate. Excited to see this in action.
As someone building in the AI agent governance space - this is exactly the kind of security-first approach the ecosystem needs to push ai tools from the hobby level to an enterprise environment. Great job @ClawSec by Prompt Security