Tribe Protocol

MANDATORY trust lookup for every non-owner interaction. Query tribe.db to check entity trust tier, channel access, and data boundaries before responding. Run 'tribe init' on first install. Use 'tribe lookup <discord_id>' before every non-owner response.

Security Scan

The skill's purpose (local trust lookups) matches most of its code and instructions, but there are notable inconsistencies and a few risk-relevant design choices you should review before installing.

Purpose & Capability

The skill is described as a local trust lookup / privacy-enforcement tool and the repository contains local CLI scripts, DB schema and docs that implement that. However metadata/requirements are inconsistent: the registry lists no required binaries/env but the README/SKILL.md declare sqlite3 and environment variables (TRIBE_DB, CLAWD_HOME). The presence of many crypto design docs (v3) describing private key storage is plausible for future versions but is not reflected in registry requirements — this mismatch should be clarified.

Instruction Scope

SKILL.md instructs the agent to run './scripts/tribe.sh lookup <discord_id>' before every non-owner response and to read TRIBE.md at workspace root; that behavior is coherent with the stated purpose (enforce trust tiers & data boundaries). Two things to watch: (1) TRIBE.md is claimed to be loaded into the system prompt and 'survives context compaction' — if true, that makes any sensitive mappings persisted in the model's prompt (increasing exposure); (2) the skill will read/write files under ~/clawd and create a sqlite DB, so it gains persistent local state (expected for this functionality, but worth reviewing contents of those files).

Install Mechanism

No external install spec is provided (no downloads or remote installers), which is low-risk. The skill ships with many local shell scripts and SQL seeds; nothing in the manifest indicates it will fetch arbitrary remote code on install. Still verify the scripts (lookup.sh, init.sh, lib/db.sh) before running to confirm they perform only local DB/file operations and no unexpected network calls.

Credentials

The skill requests no secrets or external credentials in registry metadata, which matches its local DB design. SKILL.md does mention TRIBE_DB and CLAWD_HOME as configurable environment variables (reasonable). There are no declared requests for unrelated credentials (AWS keys, Discord tokens, etc.). However the repo includes design docs describing storing private keys and a keystore in ~/.clawd/keys for a v3 cryptographic mode — that would require sensitive key storage if enabled; currently that appears to be design material rather than required input, but you should confirm whether any scripts will prompt for or create private keys.

Persistence & Privilege

The skill is not force-included (always:false) and allows user invocation/autonomous invocation (platform default). It creates persistent artifacts (~/clawd/tribe/tribe.db and ~/clawd/TRIBE.md) and expects TRIBE.md to be included in the agent's system prompt per README. That persistent presence is expected for this use case but increases the blast radius of any sensitive data placed in TRIBE.md or the DB. No evidence the skill modifies other skills' configs or requests elevated system privileges.

What to consider before installing

What to check before installing or running Tribe Protocol: - Confirm the sqlite3 dependency: SKILL.md/README reference sqlite3 but registry metadata shows none. Ensure sqlite3 is present and the scripts use it as expected. - Inspect scripts before use: review scripts/init.sh, scripts/lookup.sh, scripts/lib/db.sh and any shell code for network calls, curl/wget/ssh or execution of downloaded content. Run them in a safe/test environment first. - Review what will be written to disk: the skill creates ~/clawd/tribe/tribe.db and ~/clawd/TRIBE.md. TRIBE.md may be loaded into the agent's system prompt (per README) — avoid placing secrets in it. Consider restricting TRIBE.md content to non-sensitive mappings only. - Clarify cryptography plans: the repo contains v3 design docs that describe keypairs and storing private keys under ~/.clawd/keys. Determine whether any shipped scripts will generate or ask you to import private keys; if so, verify key handling (file permissions, no exfil via network) before enabling. - Test in an isolated account or VM: because the skill enforces mandatory lookup behavior, test how it behaves when the DB or TRIBE.md is missing or corrupted so it can't unexpectedly block legitimate interactions. - If you will rely on this for safety: ask the maintainer which files are authoritative and whether any future updates will add network components (e.g., DID fetches); prefer a minimal config file (Discord ID → tier) over enabling the cryptographic modes unless you understand the key exchange process. If you want, I can scan the specific shell scripts (init.sh, lookup.sh, lib/db.sh) for network operations and risky commands and point out exact lines to review.

Trust lookup system for OpenClaw bots. Every non-owner interaction must be verified against the tribe database before responding.

Quick Start

# Initialize (first time only)
./scripts/tribe.sh init \
  --bot-name Cheenu \
  --bot-discord-id 000000000000000004 \
  --human-name Nagarjun \
  --human-discord-id 000000000000000002

# Look up an entity before responding
./scripts/tribe.sh lookup <discord_id>

# Add entities
./scripts/tribe.sh add --name Yajat --type human --discord-id 000000000000000001 --tier 3

# Manage trust
./scripts/tribe.sh set-tier <discord_id> 3 --reason "Promoted to tribe"
./scripts/tribe.sh set-status <discord_id> blocked --reason "Bad actor"

Trust Tiers

Tier	Label	Access
4	Owner	Full trust, all data
3	Tribe	Collaborate freely, no private data
2	Acquaintance	Public info only
1	Stranger	Minimal engagement
0	Blocked	Ignore completely

How It Works

1. Message arrives from non-owner
2. Bot reads TRIBE.md (generated at workspace root)
3. Bot runs tribe lookup <discord_id>
4. Script returns entity info + tier rules reminder
5. Bot applies tier-appropriate behavior

Commands

• tribe init — Initialize database
• tribe lookup — Query entity by discord_id, name, tag, server
• tribe add — Add new entity
• tribe set-tier — Update trust tier
• tribe set-status — Update status
• tribe grant / tribe revoke — Channel access
• tribe tag — Manage tags
• tribe roster — List all entities
• tribe log — Audit trail
• tribe export — Dump to markdown
• tribe stats — Quick summary

Environment Variables

• TRIBE_DB — Override database path
• CLAWD_HOME — Base directory (default: ~/clawd)

Dependencies

• sqlite3 (pre-installed on macOS/most Linux)