ClawHub

AIProx Orchestrator

v2.2.0

Run complex tasks using multiple AI agents simultaneously. 15 agents live. Supports workflows, web-search, email, and image generation. Requires spend_token...

⭐ 0· 250·3 current·3 all-time
by@unixlamadev-spec
MIT-0
Download zip
LicenseMIT-0 · Free to use, modify, and redistribute. No attribution required.
Security Scan
VirusTotalVirusTotal
Benign
View report →
OpenClawOpenClaw
Benign
medium confidence
✓
Purpose & Capability
Name/description (multi-agent orchestrator) align with the runtime instructions which call aprox.dev and route subtasks to specialist agents. The single required environment variable (AIPROX_SPEND_TOKEN) is consistent with a paid orchestration API. Minor documentation inconsistencies (e.g., '15 agents live' vs 'decomposes into subtasks (up to 7)') and the SKILL metadata not marking the primary credential are small editorial issues but do not indicate functional mismatch.
✓
Instruction Scope
SKILL.md instructs only HTTP POSTs to https://aiprox.dev/api/orchestrate with the spend token in the request body. It does not direct the agent to read local files, other env vars, or to contact unexpected endpoints. It does describe agent capabilities (scraping, code-audit, email) which are performed by the remote service — those remote agents may themselves crawl sites or run code, so users should avoid submitting sensitive private data to the service.
✓
Install Mechanism
Instruction-only skill with no install spec and no code files. This is the lowest-risk install model: nothing is downloaded or written to disk by the skill bundle itself.
ℹ
Credentials
The skill requires a single secret, AIPROX_SPEND_TOKEN, which is proportionate for a paid orchestration API. Note: the token is a billing/authorization secret — verify it is a scoped spend-only token (not a full account password or long-lived admin key). The SKILL metadata does not mark a 'primary credential' explicitly, but the declared env var matches the instructions.
✓
Persistence & Privilege
always:false (default) and normal autonomous invocation settings. The skill does not request persistent system presence or access to other skills' configs.
Assessment
This skill appears internally consistent, but it calls a third‑party paid API that will spend sats when you provide the spend token. Before installing: (1) verify you trust https://aiprox.dev and understand its billing model; (2) use a scoped, spend-only Lightning token (not full account credentials); (3) run dry_run mode first (the SKILL.md mentions dry_run) to preview routing before spending; (4) avoid submitting private credentials, secrets, or private source code/repos unless you trust the service and its privacy/security terms; (5) if you need stronger assurance, ask the publisher for token-scoping details, an auditable privacy policy, or a verifiable source repository.

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

latestvk973dek8dryka3kdeg43szntm582taf0

License

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

Runtime requirements

⚡ Clawdis
EnvAIPROX_SPEND_TOKEN

Comments