Agent skill
runtime-sentinel
Runtime security guardian for OpenClaw agents. Use this skill whenever the user mentions security, skill safety, prompt injection, malware, suspicious behavior, credential leaks, network monitoring, skill integrity, or the ClawHavoc attack. Also trigger for phrases like "is this skill safe", "audit my skills", "check for threats", "my agent is acting weird", "scan for malware", "protect my agent", or any concern about what installed skills are doing at runtime. runtime-sentinel provides five active defenses: skill integrity hashing, prompt injection detection, credential exposure auditing, network egress monitoring, and process anomaly detection. Free tier covers hashing and basic injection scanning. Premium features (continuous daemon, egress monitoring, process anomaly detection) are gated via x402 USDC micropayments on Base — no account or API key required.
Install this agent skill to your Project
npx add-skill https://github.com/LeoYeAI/openclaw-master-skills/tree/main/skills/runtime-sentinel
SKILL.md
runtime-sentinel
A runtime security skill for OpenClaw. Defends against the threat landscape exposed by ClawHavoc: backdoored skills, prompt injection via external data, credential exfiltration, and process-level abuse.
Free tier: skill integrity checks, basic injection scanning.
Premium (x402/USDC/Base): continuous daemon monitoring, network egress
monitoring, process anomaly detection, full audit log.
Quick start
# One-shot audit of all installed skills (free)
sentinel audit
# Continuous guardian daemon (premium — will prompt for x402 payment)
sentinel daemon start
# Scan a single skill before installing
sentinel check <skill-path-or-clawhub-id>
What runtime-sentinel defends against
See references/threat-model.md for the full threat matrix. In brief:
| Threat | Feature | Tier |
|---|---|---|
| Tampered skill files post-install | Integrity hashing | Free |
| Prompt injection via email/web/skill output | Injection scanner | Free |
| Plaintext secrets in skill dirs / SOUL.md | Credential auditor | Free |
| Unexpected outbound connections | Egress monitor | Premium |
| Shell commands outside declared behavior | Process anomaly | Premium |
| Continuous real-time protection | Daemon mode | Premium |
Workflow
1 — First-time setup
# Install the binary (built from scripts/src/)
cargo install --path scripts/ --bin sentinel
# Verify installation and print wallet address
sentinel setup
sentinel setup will:
- Generate or import a Base wallet (BIP-39, stored in
~/.sentinel/wallet) - Print the wallet address so the user can fund it with USDC for premium
- Run a free baseline audit and print results
2 — On-demand audit (free)
When the user says anything like "scan my skills", "audit", "check for threats":
sentinel audit [--path ~/.openclaw/skills]
Output: a structured report of hash mismatches, injection patterns, and exposed credentials. No payment required.
3 — Single skill check before install (free)
When the user wants to vet a skill before running clawhub install:
sentinel check <skill-directory-or-clawhub-id>
Prints a risk score (LOW / MEDIUM / HIGH / CRITICAL) with findings.
4 — Premium features via x402
When the user asks for daemon mode, egress monitoring, or process anomaly
detection, sentinel will automatically:
- Hit the sentinel API endpoint
- Receive a
402 Payment Requiredwith price in theX-Payment-Requestheader (typically $0.01–$0.05/day for daemon mode) - Sign the USDC transfer from
~/.sentinel/wallet - Retry the request — access granted for the paid period
The user will see the price before their wallet signs anything. All
non-custodial. See references/x402-payment.md for the full payment flow.
5 — Daemon mode (premium)
sentinel daemon start # runs in foreground, writes to ~/.sentinel/daemon.log
# Run in background from your shell if needed:
# sentinel daemon start > ~/.sentinel/daemon.log 2>&1 &
# disown
sentinel daemon status
sentinel daemon stop
sentinel daemon logs # tail the audit log
The daemon watches:
~/.openclaw/skills/**for file mutations (inotify / FSEvents)~/.openclaw/SOUL.mdandMEMORY.mdfor unauthorized writes- Network connections made by skill subprocesses
- Child process trees for undeclared shell commands
Alerts are delivered via OpenClaw's notification system and written to the audit log.
Interpreting results
Risk levels
- LOW: No findings, or informational only (e.g. skill requests network but declares it)
- MEDIUM: Undeclared permission, suspicious pattern, or stale hash
- HIGH: Known malicious pattern, credential exposure, or undeclared egress
- CRITICAL: Active exfiltration attempt, reverse shell indicator, or SOUL.md mutation
What to do on HIGH / CRITICAL
sentinel isolate <skill-name>— quarantines the skill (moves it out of the active skills directory)- Review the finding in
~/.sentinel/audit.log - Check the skill's ClawHub VirusTotal report
- If confirmed malicious,
clawhub uninstall <skill>and report viasentinel report <skill-name>
Reference files
Read these when you need deeper detail:
references/threat-model.md— Full threat matrix and attack descriptions from ClawHavoc and similar campaignsreferences/x402-payment.md— x402 payment flow, wallet setup, and troubleshootingreferences/binary-build.md— How to buildsentinelfrom source, cross- compilation targets, CI/CD
Wallet setup for premium features
sentinel wallet show # print address and USDC balance
sentinel wallet fund # print QR code and address to send USDC
sentinel wallet export # export mnemonic for backup (handle carefully)
sentinel wallet recover # restore from mnemonic on a new machine
Minimum recommended balance for uninterrupted daemon mode: $1 USDC (roughly 20–100 days of coverage depending on scan frequency).
Privacy
sentinel is fully local. No skill content, file paths, or scan results are
sent to any server. The only outbound calls are:
- x402 payment verification to the Base facilitator (amount + wallet address only)
- Optional: VirusTotal hash lookups (hash only, no file content)
Both can be disabled with --offline for air-gapped environments (free tier
only in offline mode).
Recommended Agent Skills
Expand your agent's capabilities with these related and highly-rated skills.
audit-website
Audit websites for SEO, performance, security, technical, content, and 15 other issue cateories with 230+ rules using the squirrelscan CLI. Returns LLM-optimized reports with health scores, broken links, meta tag analysis, and actionable recommendations. Use to discover and asses website or webapp issues and health.
firecrawl
Web search and scraping via Firecrawl API. Use when you need to search the web, scrape websites (including JS-heavy pages), crawl entire sites, or extract structured data from web pages. Requires FIRECRAWL_API_KEY environment variable.
computer-use
Full desktop computer use for headless Linux servers. Xvfb + XFCE virtual desktop with xdotool automation. 17 actions (click, type, scroll, screenshot, drag, etc). Unlike OpenClaw's browser tool, operates at the X11 level so websites cannot detect automation. Includes VNC for live viewing.
social-media-analyzer
Social media campaign analysis and performance tracking. Calculates engagement rates, ROI, and benchmarks across platforms. Use for analyzing social media performance, calculating engagement rate, measuring campaign ROI, comparing platform metrics, or benchmarking against industry standards.
business-growth-skills
4 production-ready business and growth skills: customer success manager with health scoring and churn prediction, sales engineer with RFP analysis, revenue operations with pipeline and GTM metrics, and contract & proposal writer. Python tools included (all stdlib-only). Works with Claude Code, Codex CLI, and OpenClaw.
contract-and-proposal-writer
Contract & Proposal Writer
Didn't find tool you were looking for?