← Back to Skills Marketplace
6659
Downloads
2
Stars
0
Active Installs
17
Versions
Install in OpenClaw
/install guard-scanner
Description
Security scanner and runtime guard for OpenClaw skills, MCP servers, and AI agent workflows. Detects prompt injection, identity hijacking, memory poisoning,...
Usage Guidance
Review or fix the ClawHub audit command-injection issue before using this with untrusted input. Treat the malicious fixture files as hazardous test samples and do not execute them directly. Also verify a built package before installation because this source artifact did not include the compiled plugin and launcher files referenced by package metadata.
Capability Assessment
Credentials
src/asset-auditor.ts runs execSync with a shell-interpolated ClawHub query from the CLI, making command execution possible if untrusted query text reaches guard-scanner audit clawhub.
Install Mechanism
package.json has no normal install lifecycle script and its files list excludes tests, but the inspected source artifact is missing referenced build outputs and launcher files such as dist/openclaw-plugin.mjs and guard-scanner, so the install surface is not fully verifiable from this artifact.
Instruction Scope
The root skill instructions describe user-invoked scanning, audit, MCP, and runtime guard workflows; the prompt-injection and credential-theft text appears in malicious test fixtures, not in the root runtime instructions.
Persistence & Privilege
Long-running watch/patrol modes, MCP async task files, and audit logs under ~/.openclaw/guard-scanner are disclosed and purpose-aligned; I did not find hidden cron, service, or backdoor persistence in the runtime path.
Purpose & Capability
The stated purpose, root SKILL.md, MCP tools, runtime hook, and scanner implementation are broadly coherent for a security scanning and runtime guard package.
How to Use
- Make sure OpenClaw is installed (local or Docker)
- Run the install command in chat:
/install guard-scanner - After installation, invoke the skill by name or use
/guard-scanner - Provide required inputs per the skill's parameter spec and get structured output
Version History
v16.0.2
Improve ClawHub listing copy for search/discovery, align metadata with v16.0.2 metrics, and keep SKILL/package/plugin versions in sync.
v16.0.1
v16.0.1: 5-layer analysis pipeline, OWASP ASI compliance, 358 patterns, 35 categories, 27 runtime checks
v15.0.0
v15.0.0: 358 patterns, 35 categories, 27 runtime checks, 332 E2E tests. Unicode confusable, Base64 scan, ContextCrush gate.
v13.0.1
Fix SKILL.md frontmatter for OpenClaw compatibility. Add Finding Schema. 306 tests passing. SSOT aligned.
v5.0.8
v5.0.8
v5.0.7
v5.0.7: Improved ClawHub search visibility. Keyword-enriched description for scanner/security/skill queries. Updated stats: 150 patterns, 139 tests, 5 CVEs covered.
v5.0.6
v5.0.6: CVE-2026-2256 (MS-Agent check_safe bypass, CERT VU#431821) + CVE-2026-25046 (Kimi execSync injection). 150 patterns, 139 tests.
v5.0.5
v5.0.5: 147 patterns (23 categories), 136 tests, CVE-2026-25905/27825, VDB Injection, QuarantineNode, OSS cleanup
v5.0.4
v5.0.4: Stealth-encoded signatures to avoid static scanner false positives. 134/134 tests. Logarithmic decay for duplicate findings.
v5.0.3
v5.0.3: Added openclaw.hooks field for npm hook pack distribution — users can now run 'openclaw hooks install guard-scanner' directly
v5.0.2
v5.0.2: Added handler.ts for OpenClaw hooks compatibility — fixes openclaw hooks install
v5.0.1
v5.0.1: Pure OSS release — removed all proprietary references, 135 static + 26 runtime patterns, 22 categories, zero dependencies
v4.0.2
guard-scanner 4.0.2 introduces major upgrades with expanded runtime protection and improved performance.
- Added full runtime blocking of dangerous tool calls via OpenClaw plugin hook (26 patterns, 5 layers, 0.016ms/scan)
- Runtime Guard enforcement modes (`monitor`, `enforce`, `strict`) are now fully functional (blocking supported)
- Increased pattern library: 135 static + 26 runtime patterns, covering 22 threat categories
- Expanded and clarified documentation; now includes clear requirements for `--soul-lock` identity protection
- Test suite greatly extended to 134 tests across 24 suites
- No network access or dependencies; scanning remains fully local and deterministic
v2.1.0
guard-scanner 2.1.0
- Enhanced documentation and onboarding: added detailed OpenClaw integration/limitations, step-by-step start, and clarified runtime mode status.
- New task lists, docs, and sample fixture skills added for maintainers.
- Updated test coverage to include new fixture examples of leaky/PII risks.
- Improved terminology: now explicitly identifies current runtime guard as "warn-only" until OpenClaw `cancel` API lands.
- Documentation now clearly reflects that no network or model calls occur, and local-only audit logging remains unchanged.
v2.0.1
docs: README updated for v2.0.0 — Security Gaps section, test counts, roadmap
v2.0.0
feat: Plugin Hook runtime guard with actual blocking. 3 modes: monitor/enforce/strict. 35 new tests.
v1.0.0
🛡️ Initial release: 170+ threat patterns, 17 categories, Runtime Guard hook, SARIF/HTML/JSON output, Plugin API. Zero dependencies.
Metadata
Frequently Asked Questions
What is Guard Scanner?
Security scanner and runtime guard for OpenClaw skills, MCP servers, and AI agent workflows. Detects prompt injection, identity hijacking, memory poisoning,... It is an AI Agent Skill for Claude Code / OpenClaw, with 6659 downloads so far.
How do I install Guard Scanner?
Run "/install guard-scanner" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.
Is Guard Scanner free?
Yes, Guard Scanner is completely free, licensed under MIT-0. You can download, install and use it at no cost.
Which platforms does Guard Scanner support?
Guard Scanner is cross-platform and runs anywhere OpenClaw / Claude Code is available (cross-platform).
Who created Guard Scanner?
It is built and maintained by dee-guava (@koatora20); the current version is v16.0.2.
More Skills