Tool
GitHub - prompt-security/clawsec: A complete security skill suite for OpenClaw, Hermes, PicoClaw and NanoClaw agents (and variants). Protect your SOUL.md (etc') with drift detection, live security recommendations, automated audits, and skill integrity verification. All from one installable suite.
Publication date not yet evaluated · Added github.com
Page published
Coverage timeline
Single-source analysis — one report is available.
Why it matters
clawsec targets a real defensive gap for AI agent deployments by verifying skill integrity and detecting configuration drift, giving defenders a way to harden agent instruction files and catch tampering or supply-chain manipulation.
clawsec, published by prompt-security on GitHub, is an installable security skill suite for AI coding agents (referred to as OpenClaw, Hermes, PicoClaw and NanoClaw) that provides drift detection, live security recommendations, automated audits, and skill integrity verification for agent configuration files such as SOUL.md. The repository includes automated NVD/GHSA advisory syncing and packaged, npx-installable skills for hardening agent setups.