Convoloai
v1.0.2Convolo.ai integration. Manage Leads, Persons, Organizations, Deals, Projects, Activities and more. Use when the user wants to interact with Convolo.ai data.
⭐ 0· 118·0 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 is an integration for Convolo.ai and its runtime instructions consistently use the Membrane CLI to perform connector actions and proxy raw API calls. However, the registry metadata claims no required binaries while SKILL.md explicitly instructs installing the @membranehq/cli (npm) — a small inconsistency between metadata and runtime instructions.
Instruction Scope
SKILL.md stays within the stated purpose (listing actions, running actions, creating connections, proxying requests). It explicitly recommends using Membrane for auth and not asking users for API keys. Be aware the documented actions include potentially destructive or sensitive operations (delete-project-contacts, initiate-call, proxy raw requests) which will perform changes in the user's Convolo.ai environment if run.
Install Mechanism
There is no install spec in the registry, but the instructions ask the operator to run an npm global install of @membranehq/cli. Installing a public npm CLI is a common pattern but carries moderate risk versus instruction-only skills (verify the package source, prefer official releases and non-root installation).
Credentials
No environment variables or credentials are requested by the skill; authentication is delegated to Membrane's login flow. This is proportionate to the stated purpose.
Persistence & Privilege
The skill does not request always:true and does not modify other skills or system-wide configs. Note that model invocation is allowed (platform default) — because the skill can trigger actions that modify remote data, consider controlling or reviewing autonomous runs.
Assessment
This skill is coherent for integrating Convolo.ai through Membrane, but before installing or running it: 1) verify @membranehq/cli on npm (publisher, package versions) and install it in a safe environment (non-root or a container) if you proceed; 2) create and test a Membrane connection in a sandbox or test tenant first; 3) be cautious with actions that change data or initiate calls (delete, initiate-call, proxy requests) — run query/list actions first to confirm targets; 4) prefer manual confirmation before allowing the agent to invoke destructive actions autonomously, and review Membrane audit logs for activity after use; 5) note the metadata omission (required binary not declared) — treat the SKILL.md instructions as authoritative for runtime prerequisites.Like a lobster shell, security has layers — review code before you run it.
latestvk971taar05zdcfnax7bybj5tr5842f0h
License
MIT-0
Free to use, modify, and redistribute. No attribution required.