trypto1019 skills on Remote OpenClaw

arc-security-audit

Runs a full security audit of all installed OpenClaw skills in a single pass. Chains arc-skill-scanner, arc-trust-verifier, and SHA-256 binary integrity checks, then outputs a prioritized risk report with per-skill trust scores. Optionally generates trust attestations for skills that pass all checks.

arc-workflow-orchestrator

Runs sequences of skills as automated pipelines defined in YAML or JSON. Each step supports conditional execution, failure handling (abort, warn, rollback, retry), output passing between steps, and optional audit logging. A dry-run mode shows what would execute without running anything.

arc-trust-verifier

Assesses the trustworthiness of a ClawHub skill by analyzing publisher reputation, version consistency, content integrity, and dependency chains. Produces trust scores across five levels from VERIFIED to UNTRUSTED. Generates and verifies signed attestations that can be stored or audited.

arc-memory-pruner

Prunes and compacts agent memory files to prevent unbounded growth. Enforces line limits, rotates log directories with a circular buffer, and removes stale state entries by date. Includes a dry-run mode to preview changes before applying them.

arc-department-manager

Organize AI sub-agents into named departments with assigned models and task queues. Delegate tasks by department, track status, and generate summary reports across the full team. Built for autonomous workflows where multiple domains need to run in parallel.

arc-agent-lifecycle

Tracks the full history of an autonomous agent's configuration, installed skills, and changes over time. Takes point-in-time snapshots, diffs two states, and rolls back to earlier configurations. A retirement log records why skills were removed and what replaced them.

arc-skill-scanner

Scans OpenClaw skill packages for security vulnerabilities before installation. Detects credential stealers, obfuscated code, data exfiltration, prompt injection in SKILL.md files, and binary tampering. Roughly 22-26% of ClawHub skills have been flagged as containing vulnerabilities.

arc-skill-sandbox

Runs untrusted skills in a monitored environment before installation. Tracks filesystem access, environment variable reads, network connections, and subprocess calls during execution. Produces a JSON report with a safety verdict (SAFE / SUSPICIOUS / DANGEROUS).

arc-free-worker-dispatch

Routes tasks to free AI models via OpenRouter, delegating content writing, research, and code generation away from expensive primary models. Supports single tasks, typed dispatch for automatic model selection, and batch processing from a JSON file.

arc-security-mcp

Security intelligence service for the AI agent ecosystem, accessed via MCP SSE endpoint. Queries a database of known-dangerous skills, scans source code against 25 pattern rules, and runs LLM-powered intent analysis on SKILL.md files to detect mismatches and social engineering. Built from 743+ findings across 361+ real ClawHub skill audits.

arc-skill-differ

Compares two versions of an OpenClaw skill to surface security-relevant changes introduced between releases. Detects new network access, credential reads, code execution patterns, data exfiltration, and suspicious file additions. Produces a SAFE, REVIEW, or BLOCK recommendation based on what changed.

arc-skill-health-monitor

Monitors deployed skills for performance drift, errors, and unexpected behavior changes. Tracks latency percentiles, error rates, output format changes, and resource usage across invocations. Health data is stored locally per skill with configurable alerting thresholds.

arc-compliance-audit

Immutable, hash-chained audit logging for autonomous agent operations. Each entry records what happened, which agent did it, and a SHA-256 hash linking to the previous entry so any tampering breaks the chain. Covers skill executions, decisions, data access, and budget changes.

arc-wake-state

Saves agent state to structured files so autonomous agents can resume work after context window resets or crashes. Provides a persistent task queue, named checkpoints, and crash detection based on heartbeat timestamps.

arc-metrics-dashboard

Records operational metrics for agents: API calls, task completions, errors, and timed durations. Generates text-based dashboards and exports data as JSON or CSV. Data is stored as daily JSON files in ~/.openclaw/metrics/ with no database required.

arc-budget-tracker

Tracks every transaction an agent makes, enforces spending limits, and warns before the budget runs out. Stores data locally in JSON and exposes commands for logging, checking, summarizing, and exporting expenses.

arc-compliance-checker

Policy-based compliance assessment for OpenClaw skills. Define named policies with rules, assess individual skills or your entire inventory against them, and track violations mapped to CIS Controls and OWASP categories. Supports exemptions and remediation tracking.