xmtp-comms-guard
Skill112 starsChanged 3 months agoMITView on GitHub
Security middleware for all XMTP communications in EverClaw. Enforces guarded client usage with validation, integrity checks, and fail-closed security policies. Integrates approval flows for sensitive operations. Use when integrating XMTP messaging, configuring communication security, or auditing guarded client enforcement.
In this repository14 other files it gives its agents.
- AGENTS.mdAGENTS.md
- cron-packsSkill
- memory-upgradeSkill
- mission-controlSkill
- everclawSkill
- agent-chatSkill
- bagmanSkill
- night-shiftSkill
- pii-guardSkill
- prompt-guardSkill
- relationshipsSkill
- skillguardSkill
- three-shiftsSkill
- three-shiftsSkill
The file
We split this skill into the rules it gives an agent
2 rules. About 0 are common, 2 are distinctive, and 0 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈2
Distinctive · estimate
This author's own choices. Worth a look.
0
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 14
All XMTP communication MUST go through the guarded client:
- Distinctive: line 37
No runtime interception of raw imports (honestly documented)
≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
xmtp-comms-guard — Skill Integration Guide (V6)
Type: Critical Security Version: 6.0.0 Required peer dependencies: bagman, pii-guard, prompt-guard
Mandatory Usage
All XMTP communication MUST go through the guarded client:
import { createGuardedXmtpClient } from "xmtp-comms-guard";
const { client, middleware } = await createGuardedXmtpClient(rawClient, userWallet);Raw @xmtp/client imports are blocked by ESLint rules and SkillGuard scan.
Three-Shift Integration
Three-Shift = EverClaw's standard approval flow with three options:
- Approve — allow the action
- Redact — downgrade/sanitize
- Block — deny the action
Used for: peer revocation review, key rotation re-approval, introduction chain re-evaluation.
Enforcement Model
Enforcement is convention-based + build-time gates:
- ESLint rule blocks
@xmtp/clientdirect imports - SkillGuard scan detects raw client usage patterns
- No runtime interception of raw imports (honestly documented)
See enforcement.md for full details.
Fail-Closed Conditions
The skill refuses to operate when:
- Hash chain integrity check fails on startup
- SQLCipher encryption check fails
- Nonce cache detects replay
- Unknown topic in message
- Unknown sensitivity level
- Message exceeds 64KB
- Protocol version is not "6.0"
- Peer not in registry or blocked
Threat Model
Covered in threat-model.md:
- Malicious external agent → blocked by schema + checks
- Compromised internal agent → blocked by middleware + SkillGuard gates
- Host compromise → limited by Bagman + HMAC chain + fail-closed
- Replay attacks → nonce cache (90s TTL) + hash chain
- Data exfiltration → PII Guard + trust context rules
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.