ClawHub

Personal Agent Network

v0.1.1

Design patterns for personal agents coordinating like executive assistants—delegation manifests, relationship handshakes, commitment tiers, trust, and OpenCl...

⭐ 0· 66·0 current·0 all-time
byMadhav@madhavuf
MIT-0
Download zip
LicenseMIT-0 · Free to use, modify, and redistribute. No attribution required.
Security Scan
VirusTotalVirusTotal
Benign
View report →
OpenClawOpenClaw
Benign
high confidence
✓
Purpose & Capability
The name/description (personal agent network, delegation manifests, handshakes) aligns with the SKILL.md content. The skill declares no binaries, env vars, or installs and does not attempt to access unrelated services or credentials.
✓
Instruction Scope
SKILL.md is purely prescriptive/documentary: it defines artifacts, protocols, tiers, and onboarding rules. It explicitly forbids running shell/ClawHub unless the user explicitly requests it and contains no instructions to read files, exfiltrate data, or call external endpoints.
✓
Install Mechanism
No install specification or code files are present (instruction-only), so nothing will be written to disk or downloaded by the skill itself.
✓
Credentials
The skill requests no environment variables or credentials. It references identity concepts (principal_id, agent_id) conceptually but does not attempt to obtain or require secrets.
✓
Persistence & Privilege
The skill is not always-on and uses default autonomous invocation settings (normal for skills). It does not request persistent system privileges or modify other skills' configs.
Assessment
This skill is documentation-only and internally consistent with its stated purpose — safe to install in that it won't by itself run code or ask for secrets. Before installing or enabling widely: (1) confirm the published source/repo and publisher identity (metadata shows an OpenClaw homepage but source is unknown), (2) review future versions for any added install specs or environment requirements, and (3) when you publish or run ClawHub commands follow the guidance to run the ClawHub CLI yourself on your machine rather than letting an agent execute shell commands automatically.

Like a lobster shell, security has layers — review code before you run it.

latestvk97e50bzp7wevc48ksazyrqn8183kanb

License

MIT-0
Free to use, modify, and redistribute. No attribution required.
Termshttps://spdx.org/licenses/MIT-0.html

Runtime requirements

🤝 Clawdis

Comments