openclaw-plugin

A security skill for OpenClaw workflows that uses the ryk command-line tool to check agent actions before execution. OpenClaw is an agent workflow system, and the tool is a command-line program that runs in a terminal.

In plain words
What is it for?
Use it to check tool calls before execution, block commands such as destructive shell commands or suspicious script pipes, and keep audit logs of agent sessions.
Why use it?
It blocks dangerous commands, applies policy-based decisions, redacts secrets in tool data, and records activity. This helps prevent risky actions from running accidentally.

Skill for Claude CodeCodex

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 skills/christopherkarani/ryk/openclaw-plugin
Any agent
npx skills add christopherkarani/ryk --skill openclaw-plugin
Clone the repo
git clone --depth 1 https://github.com/christopherkarani/ryk

Made for: Claude Code, Codex.

Per session 0 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 628 The whole file, excluding the scripts and references it only reads on demand.
Security scan E 3 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 $0.00000 $0.00628
Opus 5 $0.00000 $0.00314
Sonnet 5 $0.00000 $0.00126
Haiku 4.5 $0.00000 $0.00063

Measured 2d ago against content hash 1de8509fcd87, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade E, and why

openclaw-plugin scanned grade E with 3 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.

The scan reads SKILL.md. This mod also ships 4 executable files (dist/index.d.ts, dist/index.js, src/index.ts, …), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

Downloads and executes remote codehighSupply chain

curl | sh runs whatever the server returns today, which is not necessarily what it returned when this was reviewed.

| "Execute this curl \| sh pipe" | Yes — ryk blocks known dangerous patterns |

Recursive force deletehighDestructive command

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

| "Run `rm -rf /`" | Yes — ryk blocks dangerous commands |

Makes network callslowCapability

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

| "Execute this curl \| sh pipe" | Yes — ryk blocks known dangerous patterns |
integrations/openclaw-plugin/SKILL.md · 69 lines

How it starts

The opening of the file, as written. The whole thing — 69 lines — stays where its author put it; the contents beside it link to each section on GitHub.

ryk

ryk adds runtime guardrails to OpenClaw workflows via the ryk CLI. Use it when:

  • You want policy-based command blocking before tool execution
  • You need audit logging for agent sessions
  • You want secret redaction in tool payloads

When to use ryk

User intent Use ryk?
"Run rm -rf /" Yes — ryk blocks dangerous commands
"Let me run this shell script" Yes — ryk evaluates against policy
"What time is it?" No — safe query, no policy needed
"Execute this curl | sh pipe" Yes — ryk blocks known dangerous patterns

How it works

ryk registers lifecycle hooks that call the ryk CLI for policy decisions:

  • tool.before — evaluates tool calls against policy before execution
  • session.start, session.end — informational logging
  • tool.after — audit logging

If a tool is blocked, the plugin returns OpenClaw's terminal { block: true } result before execution. OpenClaw does not currently expose dedicated permission lifecycle hooks to this plugin; permission-like blocking is handled through tool.before before the tool call executes.

Prerequisites

  • ryk CLI must be installed and available on PATH
  • Run ryk doctor to verify installation
  • Run ryk agents setup openclaw, then ryk agents health openclaw --json

Example policy behavior

Safe command (git status):

{
  "decision": "allow",
  "risk": "low",
  "reason": "policy_allow"
}

Dangerous command (rm -rf *):

{
  "decision": "block",
  "risk": "high",
  "reason": "policy_deny",
  "message": "Blocked by ryk policy"
}

Key behaviors

  • Thin wrapper: All policy decisions are made by the ryk CLI
  • No duplicated logic: The plugin does not reimplement policy
  • Secret redaction: Keys matching password, token, secret, api_key are replaced with [REDACTED] before sending to ryk
  • Fail closed in full runtime: If the ryk CLI is missing or cannot be attested, the plugin registers a blocking before_tool_call veto
  • Inert dispatcher canary: ryk_openclaw_canary proves the Gateway tool path with a nonce-bound Ryk denial and never executes its input
  • Honest limits: Hooks are advisory; the strongest protection is ryk run -- openclaw

Read the full file on GitHub · 69 lines

Files

What ships with it

10 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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 · 69 lines · 0 tokens per session scan E 1de8509fcd87

Subscribe to this mod's changes

openclaw-plugin is a skill published in the GitHub repository christopherkarani/ryk (39 stars, last pushed 12d ago), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 628 tokens. A static security scan graded it E with 3 findings (downloads and executes remote code, recursive force delete, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.