Skip to content

Commit 55f2bbb

Browse files
author
jovanSAPFIONEER
committed
v4.11.1 - fix ClawHub scanner: tighten bundle ignore, clarify sessions_send + PII warnings
1 parent b669d6d commit 55f2bbb

File tree

7 files changed

+61
-19
lines changed

7 files changed

+61
-19
lines changed

.clawhubignore

Lines changed: 34 additions & 11 deletions
Original file line numberDiff line numberDiff line change
@@ -1,39 +1,62 @@
1-
# Only ship SKILL.md + supporting scripts + blackboard template
2-
# Exclude everything else
1+
# ClawHub bundle: ship only SKILL.md + scripts/*.py + swarm-blackboard.md + requirements.txt
2+
# Exclude everything else so TypeScript/Node.js docs don't leak into the Python-only skill bundle.
33

4-
# TypeScript source & build
4+
# ── TypeScript source & build ──
55
*.ts
66
dist/
77
lib/
88
adapters/
99
types/
10+
bin/
1011

11-
# Config & tooling
12+
# ── Node.js / config ──
1213
tsconfig.json
1314
tsconfig.build.json
1415
package.json
1516
package-lock.json
1617
node_modules/
18+
setup.ts
1719

18-
# Tests
20+
# ── Tests ──
1921
test.ts
2022
test-*.ts
2123

22-
# Docs (not needed for the skill)
24+
# ── All docs except SKILL.md ──
2325
README.md
2426
QUICKSTART.md
2527
CHANGELOG.md
2628
LICENSE
2729
CONTRIBUTING.md
2830
CODE_OF_CONDUCT.md
2931
SECURITY.md
32+
ARCHITECTURE.md
33+
ENTERPRISE.md
34+
INTEGRATION_GUIDE.md
35+
BENCHMARKS.md
36+
ADOPTERS.md
37+
AUDIT_LOG_SCHEMA.md
38+
RELEASING.md
39+
CLAUDE.md
40+
CODEX.md
41+
SHOW_HN.md
42+
AWESOME_LISTS.md
43+
claude-project-prompt.md
44+
45+
# ── Reference docs (TypeScript-specific) ──
46+
references/
47+
48+
# ── OpenAPI / tooling (TypeScript MCP server) ──
49+
openapi.yaml
50+
claude-tools.json
3051

31-
# CI/CD
52+
# ── Examples (TypeScript) ──
53+
examples/
54+
55+
# ── CI/CD ──
3256
.github/
3357

34-
# Other
58+
# ── Misc ──
3559
.gitignore
3660
.npmignore
37-
*.json
38-
setup.ts
39-
references/
61+
err.txt
62+
socket.json

CHANGELOG.md

Lines changed: 6 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -5,6 +5,12 @@ All notable changes to Network-AI will be documented in this file.
55
The format is based on [Keep a Changelog](https://keepachangelog.com/en/1.1.0/),
66
and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0.html).
77

8+
## [4.11.1] - 2026-03-22
9+
10+
### Fixed
11+
- **ClawHub scanner: "suspicious" flag** — tightened `.clawhubignore` to exclude all TypeScript docs, OpenAPI spec, examples, and AI instruction files from the Python-only skill bundle; previously 15+ doc files referencing Node.js/TypeScript features leaked into the ClawHub package, causing a doc/bundle mismatch warning
12+
- **SKILL.md clarity** — added explicit data-flow notice that `sessions_send` is NOT implemented by this skill (host-platform built-in only), added PII warning for justification fields and audit log, expanded `metadata.openclaw` with `sessions_send`, `pii_warning`, and `data_directory` fields
13+
814
## [4.11.0] - 2026-03-22
915

1016
### Added

README.md

Lines changed: 1 addition & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -5,7 +5,7 @@
55
[![Website](https://img.shields.io/badge/website-network--ai.org-4b9df2?style=flat&logo=web&logoColor=white)](https://network-ai.org/)
66
[![CI](https://github.com/Jovancoding/Network-AI/actions/workflows/ci.yml/badge.svg)](https://github.com/Jovancoding/Network-AI/actions/workflows/ci.yml)
77
[![CodeQL](https://github.com/Jovancoding/Network-AI/actions/workflows/codeql.yml/badge.svg)](https://github.com/Jovancoding/Network-AI/actions/workflows/codeql.yml)
8-
[![Release](https://img.shields.io/badge/release-v4.11.0-blue.svg)](https://github.com/Jovancoding/Network-AI/releases)
8+
[![Release](https://img.shields.io/badge/release-v4.11.1-blue.svg)](https://github.com/Jovancoding/Network-AI/releases)
99
[![npm](https://img.shields.io/npm/dw/network-ai.svg?label=npm%20downloads)](https://www.npmjs.com/package/network-ai)
1010
[![Tests](https://img.shields.io/badge/tests-1684%20passing-brightgreen.svg)](#testing)
1111
[![Adapters](https://img.shields.io/badge/frameworks-17%20supported-blueviolet.svg)](#adapter-system)

SKILL.md

Lines changed: 17 additions & 4 deletions
Original file line numberDiff line numberDiff line change
@@ -5,9 +5,10 @@ metadata:
55
openclaw:
66
emoji: "\U0001F41D"
77
homepage: https://network-ai.org
8-
bundle_scope: "Python scripts only (scripts/*.py). All execution is local."
9-
network_calls: "none from bundled scripts; platform sessions_send delegations may invoke external models"
10-
sessions_ops: "platform-provided"
8+
bundle_scope: "Python scripts only (scripts/*.py). All execution is local. No TypeScript, Node.js, adapters, or CLI tools are included in this bundle."
9+
network_calls: "none — bundled scripts make zero network calls. The host platform's sessions_send (not part of this skill) may invoke external models."
10+
sessions_send: "NOT implemented or invoked by this skill. sessions_send is a host-platform built-in. This skill only provides budget guards that run before the platform delegates."
11+
sessions_ops: "platform-provided — outside this skill's control"
1112
requires:
1213
bins:
1314
- python3
@@ -18,11 +19,21 @@ metadata:
1819
path: data/audit_log.jsonl
1920
scope: local-only
2021
description: "Local append-only JSONL file recording operation metadata. No data leaves the machine."
22+
pii_warning: "Do not include PII, secrets, or credentials in justification fields. Log entries persist on disk."
23+
data_directory:
24+
path: data/
25+
scope: local-only
26+
files: ["audit_log.jsonl", "active_grants.json", "project-context.json"]
27+
description: "All persistent state is local-only. No files are transmitted over the network."
2128
---
2229

2330
# Swarm Orchestrator Skill
2431

25-
> **Scope:** The bundled Python scripts (`scripts/*.py`) make no network calls, use only the Python standard library, and have zero third-party dependencies. Tokens are UUID-based (`grant_{uuid4().hex}`) stored in `data/active_grants.json`. Audit logging is plain JSONL (`data/audit_log.jsonl`). Workflow delegations that use the host platform's `sessions_send` may invoke external model APIs outside this skill's control.
32+
> **Scope:** The bundled Python scripts (`scripts/*.py`) make **no network calls**, use only the Python standard library, and have **zero third-party dependencies**. Tokens are UUID-based (`grant_{uuid4().hex}`) stored in `data/active_grants.json`. Audit logging is plain JSONL (`data/audit_log.jsonl`).
33+
34+
> **Data-flow notice:** This skill does NOT implement, invoke, or control `sessions_send`. That is a host-platform built-in (OpenClaw runtime). The orchestration instructions below describe *when* to call the platform's `sessions_send` after budget checks pass — but the actual network call, model endpoint, and data transmission are entirely the host platform's responsibility. If you need to prevent external network calls, disable or reroute `sessions_send` in your platform settings before installing this skill.
35+
36+
> **PII / sensitive-data warning:** The `justification` field in permission requests and the audit log (`data/audit_log.jsonl`) store free-text strings provided by agents. **Do not include PII, secrets, or credentials in justification text.** Consider restricting file permissions on `data/` or running this skill in an isolated workspace.
2637
2738
## Setup
2839

@@ -515,6 +526,8 @@ Sequential processing - output of one feeds into next.
515526

516527
**Every sensitive action MUST be logged to `data/audit_log.jsonl`** to maintain compliance and enable forensic analysis.
517528

529+
> **Privacy note:** Audit log entries contain agent-provided free-text fields (justifications, descriptions). These are stored locally in `data/audit_log.jsonl` and never transmitted over the network by this skill. However, **do not put PII, passwords, or API keys in justification strings** — they persist on disk. Consider periodic log rotation and restricting OS file permissions on the `data/` directory.
530+
518531
### What Gets Logged Automatically
519532

520533
The scripts automatically log these events:

openapi.yaml

Lines changed: 1 addition & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -6,7 +6,7 @@ info:
66
blackboard coordination, parallel agent spawning, and permission gating
77
via AuthGuardian. Requires the companion MCP server:
88
`npm install -g network-ai && npx network-ai-server --port 3001`
9-
version: 4.11.0
9+
version: 4.11.1
1010
license:
1111
name: MIT
1212
url: https://github.com/Jovancoding/Network-AI/blob/main/LICENSE

package.json

Lines changed: 1 addition & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -1,6 +1,6 @@
11
{
22
"name": "network-ai",
3-
"version": "4.11.0",
3+
"version": "4.11.1",
44
"description": "AI agent orchestration framework for TypeScript/Node.js - 17 adapters (LangChain, AutoGen, CrewAI, OpenAI Assistants, LlamaIndex, Semantic Kernel, Haystack, DSPy, Agno, MCP, OpenClaw, A2A, Codex, MiniMax, NemoClaw, APS + streaming variants). Built-in CLI, security, swarm intelligence, real-time streaming, and agentic workflow patterns.",
55
"homepage": "https://network-ai.org",
66
"main": "dist/index.js",

skill.json

Lines changed: 1 addition & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -1,6 +1,6 @@
11
{
22
"name": "SwarmOrchestrator",
3-
"version": "4.11.0",
3+
"version": "4.11.1",
44
"description": "Local Python orchestration skill: multi-agent workflows via shared blackboard file, permission gating, token budget scripts, and persistent project context. The bundled Python scripts make no network calls and have zero third-party dependencies. Workflow delegations via the host platform's sessions_send may invoke external model APIs.",
55
"author": "Network-AI Community",
66
"homepage": "https://network-ai.org",

0 commit comments

Comments
 (0)