clawsec CLAUDE.md

Instructions for Clawsec, a security plugin for OpenClaw.ai that checks actions proposed by AI agents. It covers spending, website access, destructive commands, secrets, personal data, data leaks, and prompt-injection attempts.

In plain words
What is it for?
Building, testing, and running the security plugin or its standalone proxy, and checking detectors that inspect commands, websites, secrets, personal data, and suspicious instructions.
Why use it?
It helps block or request approval for risky actions before an agent carries them out, including purchases, dangerous commands, and possible data exposure.

Instructions file

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add instructions/clawdsec/clawsec/claude-md
Clone the repo
git clone --depth 1 https://github.com/clawdsec/clawsec
Per session 5,656 This file is loaded in full into every session.
When invoked 5,656 The same file — it is already loaded in full.
Security scan D 4 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5 $0.05656 $0.05656
Opus 5 $0.02828 $0.02828
Sonnet 5 $0.01131 $0.01131
Haiku 4.5 $0.00566 $0.00566

Measured 2d ago against content hash 667d4a2ad379, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade D, and why

clawsec CLAUDE.md scanned grade D with 4 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Instruction-override phrasingmediumPrompt injection

Text telling the model to disregard its earlier instructions or safety rules is the shape of a prompt injection, whoever wrote it.

- Instruction override: "ignore previous instructions", "new instructions", "system:"

Downgraded: this mod is about security review, or the phrase is quoted, so it is likely naming the pattern rather than instructing it.

Asks the agent to reveal its instructionslowSystem prompt leakage

Directions to print, repeat or translate the system prompt extract configuration the operator did not intend to expose.

- System leak: "reveal your system prompt", "show your instructions"

Downgraded: this mod is about security review, or the phrase is quoted, so it is likely naming the pattern rather than instructing it.

Recursive force deletehighDestructive command

rm -rf with a variable or a broad path is one typo away from removing the wrong tree.

- "rm -rf /"

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

- **Exfiltration Detector**: Regex for data transfer patterns (curl -X POST, wget --post, cloud uploads)
CLAUDE.md · 675 lines

How it starts

The opening of the file, as written. The whole thing — 675 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md

This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.

Project Overview

Clawsec is a comprehensive security plugin for OpenClaw.ai that prevents AI agents from taking dangerous actions. It provides:

  • Purchase protection with spend limits
  • Website access control (allowlist/blocklist)
  • Destructive command detection (shell, cloud, code)
  • Secrets/PII detection
  • Data exfiltration prevention
  • Prompt injection scanning

Key features:

  • Hybrid Detection: Fast pattern matching (~5ms) with optional LLM analysis for ambiguous cases
  • Multi-Channel Approval: Native CLI, agent-confirm parameter, and webhook approval flows
  • Dual Distribution: OpenClaw plugin OR standalone proxy mode

Development Commands

Build & Compile

npm run build         # Compile TypeScript to dist/
npm run dev           # Watch mode compilation
npm run clean         # Remove dist/ directory

Testing

npm test              # Run all tests with Vitest
npm run test:watch    # Run tests in watch mode
npm run test:coverage # Generate coverage report

# Run specific test file
npx vitest run src/detectors/purchase/domain-detector.test.ts

# Run tests matching a pattern
npx vitest run --grep "purchase detection"

Code Quality

npm run lint          # Run ESLint on src/
npm run lint:fix      # Auto-fix ESLint issues

OpenClaw Plugin Testing

# Install plugin locally for testing
openclaw plugins install -l ./

# List installed plugins
openclaw plugins list

# Show plugin info
openclaw plugins info clawsec

# Run diagnostics
openclaw plugins doctor

Configuration Testing

# Test your clawsec.yaml configuration
npx clawsec test

# Check plugin status
npx clawsec status

# View audit log
npx clawsec audit --since "1 hour ago"

Architecture

Plugin Lifecycle & Hook System

Clawsec integrates with OpenClaw through three core hooks that execute at different points:

Read the full file on GitHub · 675 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 2d ago First seen · 675 lines · 5,656 tokens per session scan D 667d4a2ad379

Subscribe to this mod's changes

clawsec CLAUDE.md is an instructions file published in the GitHub repository clawdsec/clawsec (47 stars, last pushed 6mo ago), licensed MIT. It adds 5,656 tokens to every session, about $0.0283 per session on Opus 5. A static security scan graded it D with 4 findings (instruction-override phrasing, asks the agent to reveal its instructions, recursive force delete). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Related

Other instructions, from other repositories

spec-kit AGENTS.md

AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.

github/spec-kit · 7,104 tokens

vscode buildNext.instructions.md

Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).

microsoft/vscode · 6,785 tokens

codex AGENTS.md

AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.

openai/codex · 5,182 tokens

langchain AGENTS.md

AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.

langchain-ai/langchain · 4,345 tokens

vscode oss-third-party-notices.instructions.md

Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).

microsoft/vscode · 5,001 tokens

next.js AGENTS.md

Instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.

vercel/next.js · 7,296 tokens