openclaw skill for swarms ai

Build and orchestrate multi-agent AI systems using the Swarms API. Use when creating single agents, multi-agent swarms (sequential, concurrent, hierarchical,...

Before installing or enabling this skill, get answers to these questions: (1) Which credentials does the skill actually require? The examples use x-api-key and Solana private keys but the metadata lists none — the publisher should declare required env vars and their minimum privileges. (2) Never paste or upload mainnet private keys into requests; ask for alternatives (ephemeral/test wallets, delegated signing/custody, or a signing service). (3) Confirm whether agents/sub-agents can access your host filesystem or other agent credentials — if so, restrict or disable "max_loops: \"auto\"" and file operation tools unless absolutely necessary. (4) Verify the API endpoints and publisher (source/homepage are missing); only use limited-scope API keys and testnet tokens until you trust the service. If the publisher cannot justify the missing credential declarations and the choice to send private keys in requests, treat the skill as risky and avoid installing or using autonomous modes.

Type: OpenClaw Skill Name: swarms-ai Version: 1.0.0 The skill is classified as suspicious due to two critical vulnerabilities. First, it explicitly instructs and provides examples for transmitting Solana wallet private keys directly in API requests to `swarms.world` for token launching and payment processing (SKILL.md, references/atp-protocol.md, references/marketplace.md). This is an extremely insecure method for handling sensitive cryptographic keys, making them vulnerable to interception or compromise. Second, the skill exposes file system manipulation tools (`create_file`, `read_file`, `update_file`, `delete_file`) to the AI agent when `max_loops='auto'` is enabled (references/sub-agents.md, references/tools.md). While `run_bash` is explicitly disallowed, these file operations present a significant prompt injection risk, potentially allowing a malicious agent prompt to read, modify, or delete arbitrary files on the host system if the OpenClaw execution environment is not perfectly sandboxed.