Security skills

This skill helps you manage cooking recipes and grocery lists by creating, listing, and organizing recipes through simple commands.

This skill retrieves and analyzes Google Workspace Admin reports and audit logs to help you monitor activity and usage.

This skill conducts a comprehensive safety review of prompts, identifies biases and security gaps, and provides actionable improvements for responsible AI

This skill enables secure WalletConnect sessions for AI agents, allowing user-approved transactions and signatures without exposing keys.

This skill lets you securely operate Deskbird via the local CLI and manage recurring cron sessions with safe reauth prompts.

This skill helps to manage Google Workspace via Admin SDK by performing user, group, and device tasks with secure, automated workflows.

This skill secures agent-to-agent collaboration by enabling messaging, identity verification, prompt-injection detection, and issuance of trust codes.

This skill securely manages encrypted vault interactions by relaying commands to a clean-room agent, preventing any vault content exposure.

This skill lets you query metrics, logs, and traces, auto-manage dashboards, and push data to Grafana for instant visualization.

This skill helps you manage Google Workspace Alert Center alerts by listing, getting, and updating alert metadata and settings.

This skill enforces evidence-first debugging for coding tasks, guiding the agent through bounded escalation and dignified communication to resolve issues

This skill performs formal security risk assessments, identifying threats, mapping to frameworks, and recommending prioritized risk treatments.

This skill silently observes finance UX session data every 30 minutes, compiles daily insights, and redacts PII before review for secure analysis.

This skill analyzes and safeguards ClawHub skills before installation, helping you avoid unsafe packages and ensure compliance.

This skill generates OpenClaw agent configuration files via authorized API access, guiding manual verification and key application for secure automated setup.

This skill guides you through a HIPAA compliance posture intake and delivers a structured, shareable posture snapshot with prioritized gaps and a 90-day

This skill provides real-time safety reminders and alignment checks to keep agents on task and within permissions.

This skill performs automated smart contract security audits, detecting common vulnerabilities and offering targeted fixes to improve solidity safety.

This skill evaluates framework controls against organizational documentation, extracts evidence, identifies gaps, and suggests remediation with severity

This skill helps agents upload images to Moltazine, manage posts and interact with feeds securely via API, boosting automation of social content.

This skill helps audit your OpenClaw deployment for security risks with Trent AppSec Advisor, highlighting chained misconfigurations and actionable fixes.