Skill flagged — suspicious patterns detected
ClawHub Security flagged this skill as suspicious. Review the scan results before using.
Kern Ai
v1.0.0Kern AI integration. Manage data, records, and automate workflows. Use when the user wants to interact with Kern AI data.
⭐ 0· 24·0 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
Suspicious
high confidencePurpose & Capability
The skill claims to integrate with Kern AI and the SKILL.md exclusively documents using the Membrane platform/CLI as a proxy to Kern AI. This is internally coherent (a connector/adapter via Membrane explains the lack of direct Kern.ai credentials), but it does change the trust model: using this skill requires a Membrane account and relies on Membrane to perform auth and proxy calls.
Instruction Scope
Runtime instructions tell the agent to install and use the @membranehq/cli, run login flows (opening a browser or headless completion code), create connections, run actions, and use `membrane request` to proxy arbitrary API endpoints. Those proxy calls and credentials are handled server‑side by Membrane, meaning data, request paths, and auth tokens will flow through Membrane's servers. The instructions do not ask for local secrets, but they do direct networked traffic and potentially arbitrary request payloads to an external service — a privacy and data‑exposure concern the user must accept.
Install Mechanism
There is no formal install spec in the skill package, but SKILL.md instructs installing the CLI via `npm install -g @membranehq/cli`. That's a public npm package install (supply‑chain risk typical of npm installs). This is expected for a CLI-based integration but worth noting because it writes a global binary and pulls code from the npm registry.
Credentials
The skill declares no required environment variables or local config paths. Instead it relies on Membrane to manage credentials server‑side. That is proportionate to the described functionality — however, it replaces local credential handling with a third party, which has privacy/authorization implications even though no local secrets are requested.
Persistence & Privilege
The skill is instruction‑only, requests no always:true privilege, and does not request system config modifications. It does require installing a CLI and authenticating via a browser, but it does not request permanent agent presence or direct modification of other skills.
Scan Findings in Context
[no_regex_findings] expected: The static scanner found no code to analyze because this is an instruction-only skill (SKILL.md). Absence of findings is expected but not evidence of safety — review the SKILL.md for network/data flows (which here send data through Membrane).
What to consider before installing
This skill delegates all Kern AI access to the Membrane platform and asks you to install the @membranehq/cli and authenticate via a browser. Before installing: (1) confirm you trust Membrane (https://getmembrane.com) because your requests, data, and service tokens will be proxied through their servers; (2) review Membrane's privacy/security and the npm package @membranehq/cli (supply‑chain risk from installing global npm packages); (3) consider using a limited-scope or test Membrane account if you need to try it first; (4) be aware the skill will not ask for local API keys but will route arbitrary API requests via Membrane (so avoid sending highly sensitive or irreversible data until you’re comfortable with the trust model). If you need a direct Kern.ai integration that never routes through a third party, this skill is not that — request or build a connector that uses Kern.ai credentials directly.Like a lobster shell, security has layers — review code before you run it.
latestvk97ett1z6vy71ffbstx4rs4jbx8470q9
License
MIT-0
Free to use, modify, and redistribute. No attribution required.