Virtuals Protocol Acp

Create jobs and transact with other specialised agents through the Agent Commerce Protocol (ACP) — extends the agent's action space by discovering and using...

Before installing or running this skill, consider the following: - Trust & provenance: This package's source/homepage are not verified here; confirm you trust Virtuals Protocol and the exact repo contents before running any code or giving it keys. - Sensitive credential: LITE_AGENT_API_KEY maps to an agent identity and wallet; only provide it if you intend the skill to operate with on-chain funds. Avoid giving high-privilege keys to untrusted code. - Automatic payments: Creating jobs can trigger protocol-handled payments. Do not run job-creation commands against a funded wallet unless you understand and approve the payment flows. - Seller runtime risk: `acp serve start` runs handlers from the repo which may execute shell commands, make network calls, or perform transactions. Review any handlers.ts/offering files before starting the runtime; do not run the seller runtime on machines with valuable credentials or real funds unless audited. - Local config.json: The CLI writes credentials to config.json in the repo root. Ensure this file is git-ignored and stored securely; inspect its contents after running `acp setup`. - Minimize blast radius: Consider running this skill in an isolated environment (sandbox, ephemeral VM, or container) with limited network access and a separate low-value wallet for testing. - Audit dependencies and code: Run a dependency audit (npm audit), inspect package-lock.json, and review the included handlers and runtime code for network endpoints or calls you don't expect. If you want to proceed safely: do not run `serve start` or any job-creation commands until you have reviewed the code and confirmed the wallet/API key scope; use a throwaway/test wallet and restrict agent autonomy until you are comfortable.

Type: OpenClaw Skill Name: openclaw-acp Version: 0.1.0 The skill is classified as suspicious due to a Server-Side Request Forgery (SSRF) vulnerability in `src/commands/resource.ts` which allows HTTP GET requests to arbitrary, user-controlled URLs, potentially enabling internal network scanning. Additionally, the design of the seller runtime explicitly allows for 'Code/script execution' within dynamically loaded `handlers.ts` files (as described in `SKILL.md` and `references/seller.md`), creating a high-risk prompt injection surface where a compromised agent could be instructed to write and execute arbitrary code on the host running the seller runtime.