@useai-pro

incident-responder guides users through containment, investigation, and recovery for openclaw security breaches using a structured five-phase protocol with severity levels, checklists, and quick-reference commands.

output-sanitizer redacts leaked credentials, pii, and internal paths from agent responses using regex patterns and classification rules. detects aws keys, api tokens, emails, phone numbers, database urls, and source code secrets with reporting.

skill-vetter provides a structured security audit protocol for openclaw skills, covering metadata validation, permission analysis, content scanning for red flags, and typosquat detection. execution output is deterministic but trigger phrases remain generic.

skill-guard monitors runtime behavior of active openclaw skills, flagging file access, network calls, and shell commands that deviate from declared permissions or exhibit suspicious patterns.

setup-auditor guides users through a four-step security audit of their openclaw environment, scanning for credential leaks, validating permission defaults, checking sandbox readiness, and detecting compromise signs. produces a structured report with findings and remediation checklist.

Scan your project for exposed credentials, API keys, and secrets before running OpenClaw skills. Prevents accidental

Comprehensive security auditor for OpenClaw skills. Checks for typosquatting, dangerous permissions, prompt injection,

Audit and harden your OpenClaw configuration. Checks AGENTS.md, gateway settings, sandbox config, and permission

Audit npm, pip, and Go dependencies that OpenClaw skills try to install. Checks for known vulnerabilities, typosquatting,

Audit and monitor network requests made by OpenClaw skills. Detects data exfiltration, unauthorized API calls,

Generate Docker sandbox configurations for safely running untrusted OpenClaw skills. Isolates filesystem, network,

Analyze OpenClaw skill permissions and explain exactly what each permission allows. Identifies over-privileged

Detect and neutralize prompt injection attacks in OpenClaw skill content, user inputs, and external data sources.