sst-security-control-openclaw
English · 简体中文
An open-source runtime security plugin for OpenClaw. It provides local risk detection, security event logging, and blocking of high-risk operations.
Highlights: batteries included. Runs locally out of the box — no account registration, no cloud connectivity.
Installation
Plugin marketplace
Published on the ClawHub plugin marketplace — search sst-security-control-openclaw there, or install from the CLI:
# 1. Look up the package in the marketplace (optional)
openclaw plugins search sst-security-control-openclaw
# 2. Install from the marketplace
openclaw plugins install clawhub:@zhanxing/sst-security-control-openclaw --accept-capabilities
openclaw plugins enable sst-security-control-openclaw
openclaw gateway restart
Build from source
# 1. Build the package
npm install --legacy-peer-deps
npm run build:prod
# 2. Copy the tarball to the target server
scp install/sst-security-control-openclaw-1.0.2.tgz root@server:~/.openclaw/
# 3. Install on the server (run these two commands in separate terminal sessions)
openclaw plugins install npm-pack:$HOME/.openclaw/sst-security-control-openclaw-1.0.2.tgz --accept-capabilities --force
openclaw plugins enable sst-security-control-openclaw
openclaw gateway restart
Uninstall
openclaw plugins uninstall sst-security-control-openclaw
Capabilities
- Agent session and behavior event logging (NDJSON)
- High-risk actions (reverse shells, sensitive file access, and similar) are blocked in
enforcemode; everything else is only flagged and warned - Runtime status and event panel (Control UI → SST Security Control)
Security panel
The panel shows events, interventions, assets, and policy hits. OpenClaw 9.4's Control UI hosts it in a sandboxed iframe that cannot use localStorage, so the tab itself renders blank — open the standalone panel directly:
http://<host>:<port>/openclaw-security-monitor/panel
Configuration
The default configuration shipped with a fresh install is already tuned to a production baseline and works as-is. To adjust it:
openclaw plugins config sst-security-control-openclaw --set \
"intervention.mode=audit" \
"application.enabled=true"
Key configuration options:
| Option | Default | Description |
|---|---|---|
intervention.mode | enforce | audit (log only) or enforce (block) |
application.enabled | true | Application event collection switch |
application.runtimeHooks.enabled | false | Enable runtime hooks (requires NODE_OPTIONS) |
intervention.failStrategy | fail_closed | Behavior when the intervention engine fails or times out (fail_open allow / fail_closed block) |
collector.ndjsonPath | ~/.openclaw/security-events.jsonl | Event log path |
Custom SPL Rules
Blocking is driven by SPL declarative rules (YAML, apiVersion: security.use/v1). A ready-to-use rule set ships with the package; see policies/security-policy.spl.yaml for rule examples. Before switching to enforce mode, copy the policy file to ~/.openclaw/security-policy.yaml and review the rules.
Security Events
Events are NDJSON lines. The event_type values this version actually emits, by layer.
Types prefixed with x_openclaw_ are project extensions: the platform ingest
(validate_batch) rejects whole batches containing unregistered bare-name types,
while unregistered x_<project>_ extensions pass after common-field validation.
| Layer | Event types | Requires Runtime Hooks |
|---|---|---|
| Application | agent_session_start / agent_session_end, agent_start / agent_stop, x_openclaw_subagent_start / x_openclaw_subagent_progress / x_openclaw_subagent_end, agent_message, agent_tool_call / agent_tool_result, cron_changed, x_openclaw_cron_run, code_mode_exec, reasoning | no |
| Application (file) | file_read / file_write / file_delete / file_privilege — derived from tool names (fs.readFile → file_read) | no |
| System (process) | process_start, x_openclaw_process_change / process_exit / x_openclaw_process_snapshot | process_start: yes |
| System (cgroup) | x_openclaw_cgroup_snapshot / x_openclaw_cgroup_anomaly | no (needs system.enabled) |
| System (network) | network_http | yes |
| Asset | asset_add / asset_change / asset_remove / asset_snapshot | no |
| Self-protection | x_openclaw_protection_degraded, x_openclaw_tamper_detected, x_openclaw_runtime_hook_unloaded | no |
Roadmap
- 1.0.0 · Event collection + observability + rule analysis: NDJSON event stream, Control UI panel, SPL rule security analysis
- 1.1.0 · Semantic detection SDK: introduce a standalone semantic detection SDK alongside the existing SPL rule engine to improve detection coverage
Project Home
-
Website: https://www.zhihuizhanxing.com
-
Source: https://github.com/zhanxingtai/openclaw-security-control
-
WeChat Official Account:

Support
To report a security vulnerability or request urgent support, contact us by email (please do not disclose security details in a public GitHub issue):
- Security email: support@zhihuizhanxing.com
General usage questions and feature requests go to GitHub Issues.
License
Apache-2.0 — dependency declarations are in package.json.
