Inworld Ai
v1.0.0Inworld AI integration. Manage data, records, and automate workflows. Use when the user wants to interact with Inworld AI data.
⭐ 0· 67·0 current·0 all-time
byMembrane Dev@membranedev
MIT-0
Download zip
LicenseMIT-0 · Free to use, modify, and redistribute. No attribution required.
Security Scan
OpenClaw
Benign
high confidencePurpose & Capability
The name/description (Inworld AI integration) matches the instructions (use Membrane CLI to connect, discover actions, run actions, and proxy requests to Inworld). Requiring network access and a Membrane account is coherent for this purpose; no unrelated credentials or system access are requested.
Instruction Scope
SKILL.md gives concrete CLI steps (install @membranehq/cli, login, connect, list/run actions, proxy requests). It does not instruct reading unrelated files or environment variables. It does describe the Membrane 'request' proxy which allows arbitrary API paths to be called via the connected account — this is expected for a proxy integration but worth noting because actions run under the user's connected account.
Install Mechanism
The skill is instruction-only (no install spec). It tells the user to install the Membrane CLI via 'npm install -g @membranehq/cli'. That is a reasonable, common install step but installing global npm packages has the usual supply-chain/trust implications (verify package provenance before global install).
Credentials
No environment variables, secrets, or unrelated credentials are requested. The guidance explicitly tells the user not to share API keys and to create connections so Membrane handles auth — this aligns with the stated purpose.
Persistence & Privilege
The skill is not always-enabled and does not request elevated or persistent system-wide privileges. It does not modify other skills' configs. Autonomous invocation is allowed by platform default, but that is typical and not excessive here.
Assessment
This skill appears to do what it says: use the Membrane CLI as a proxy to Inworld AI. Before installing or using it: 1) Verify the Membrane project and the @membranehq/cli package (check the official website and GitHub repo) to ensure you trust the maintainer; 2) Prefer installing the CLI in a controlled environment (container or VM) if you are cautious about global npm installs; 3) Be aware that the Membrane proxy will make API calls using your connected account — any actions executed by the agent will run with that account's permissions; 4) If you don’t trust Membrane or the package source, do not run the login/connect steps or share API keys; 5) Consider limiting agent autonomy or reviewing logs of actions run through the CLI if you plan to allow autonomous invocation.Like a lobster shell, security has layers — review code before you run it.
latestvk97acbbj15yybkde48h9g6nr1n848rm4
License
MIT-0
Free to use, modify, and redistribute. No attribution required.