Verimi
v1.0.2Verimi integration. Manage data, records, and automate workflows. Use when the user wants to interact with Verimi data.
⭐ 0· 115·0 current·0 all-time
byVlad Ursul@gora050
MIT-0
Download zip
LicenseMIT-0 · Free to use, modify, and redistribute. No attribution required.
Security Scan
OpenClaw
Benign
high confidencePurpose & Capability
The skill's stated purpose (Verimi integration) matches the runtime instructions: all actions are performed via the Membrane CLI and a Membrane account. Minor inconsistency: registry metadata declares no required binaries or install steps, but SKILL.md explicitly requires installing @membranehq/cli via npm.
Instruction Scope
SKILL.md stays within scope: it instructs installing and using the Membrane CLI to create connections, list actions, run actions, and proxy requests to the Verimi API. It does not instruct the agent to read unrelated files or environment variables. Note: the proxy command allows arbitrary API paths for the connected Verimi account, which is expected but means the agent can issue arbitrary API calls against the user's Verimi connection if authorized.
Install Mechanism
This is an instruction-only skill (no install spec). The SKILL.md asks the user to install the Membrane CLI via `npm install -g @membranehq/cli`. That is a reasonable, common install method but is not declared in the registry. Installing a global npm package has moderate risk if the package or its publish source were malicious — verify the package name, publisher, and repository before installing.
Credentials
The skill requests no environment variables or local credentials. It explicitly recommends letting Membrane handle auth server-side and not collecting API keys locally, which is proportionate for a connector integration.
Persistence & Privilege
The skill does not request persistent system privileges, always=false, and does not modify other skills or system-wide agent settings. Autonomous invocation is allowed by default (normal platform behavior).
Assessment
This skill appears to do what it says: it uses Membrane to talk to Verimi. Before installing/using it: 1) Verify you trust Membrane (@membranehq) and the package repository (check the npm package, GitHub repo, and homepage). 2) Expect to install the Membrane CLI (the registry entry omitted this); prefer installing in a controlled environment if you're unsure about global npm installs. 3) When you create a connection, review the permission scopes and prompts in the browser flow — the agent will be able to run actions and proxy arbitrary Verimi API calls on behalf of that connection. 4) If you want to prevent autonomous agent access, restrict the skill or disable autonomous invocation in your agent settings. If you want more assurance, ask the publisher to add an explicit required-binaries/install spec to the registry metadata so requirements match the SKILL.md.Like a lobster shell, security has layers — review code before you run it.
latestvk9788x6fpq7rdc3fe5jg29s2h58424q6
License
MIT-0
Free to use, modify, and redistribute. No attribution required.