No red flags found in any of the 11 categories — no credential harvesting, no data exfiltration, no curl-pipe-shell installer. Scanned against the SlowMist agent-security taxonomy, refreshed every 8 hours. Full audit →
by prompt-security · Codex Skill · ★ 1.1k
Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h
🔒 Is clawsec safe to install? View the security audit →
ClawSec: Security Skill Suite for AI Agents Secure Your OpenClaw, NanoClaw, and Hermes Agents with a Complete Security Skill Suite Brought to you by Prompt Security, the Platform for AI Security 🌐 Live at: https://clawsec.prompt.security https://prompt.security/clawsec 🌍 Translations Deutsch English Wiki indexes: DE · [E
| Stars | 1,107 |
| Forks | 113 |
| Language | JavaScript |
| Category | Codex Skill |
| License | AGPL-3.0 |
| Quality Score | 68.3829366243802/100 |
| Open Issues | 36 |
| Last Updated | 2026-09-22 |
| Created | 2026-02-05 |
| Platforms | aws, node |
| Est. Tokens | ~17k |
Looking for a clawsec alternative? If you're comparing clawsec with other codex skill tools, these 6 projects are the closest alternatives on Agent Skills Hub — ranked by topic overlap, star count, and community traction.
A personal 24x7 AI assistant like OpenClaw that runs on your messaging platforms. Send a message on WhatsApp,
ClawTeam fork fully adapted for OpenClaw — multi-agent swarm coordination with OpenClaw as the default agent
PowerMem: AI Memory Plugin— Accurate, Agile, Affordable. Make AI Agent smarter.
OpenClaw plugin implementing the A2A (Agent-to-Agent) protocol v0.3.0 — bidirectional agent communication gate
Kindly Web Search MCP Server: Web search + robust content retrieval for AI coding tools (Claude Code, Codex, C
ClawBridge is the OpenClaw Mobile Dashboard. Monitor agent's real-time thoughts, actions, track token costs, a
Explore other popular codex skill tools:
clawsec is 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, an. It is categorized as a Codex Skill with 1.1k GitHub stars.
clawsec is primarily written in JavaScript. It covers topics such as clawdbot, clawdbot-skill, hermes.
You can find installation instructions and usage details in the clawsec GitHub repository at github.com/prompt-security/clawsec. The project has 1.1k stars and 113 forks, indicating an active community.
clawsec is released under the AGPL-3.0 license, making it free to use and modify according to the license terms.
The top alternatives to clawsec on Agent Skills Hub include secure-openclaw, ClawTeam-OpenClaw, powermem. Each offers a different approach to the same problem space — compare them side-by-side by stars, quality score, and community activity.
Grades come from a rule-based scan built on the SlowMist agent-security taxonomy, covering 11 red-flag categories including credential harvesting, data exfiltration, and curl | sh installers. It is a first-layer scan, not a manual audit — we say so rather than overstate it.
The scale of the problem is documented independently: Liu et al. (2026), in a study of 31,132 agent skills, report that 26.1% contain security vulnerabilities. Our own full-catalog census is published as a citable open dataset.
Sources & who's responsible: