Skillv1.0.1

ClawScan security

Madkudu · ClawHub's context-aware review of the artifact, metadata, and declared behavior.

BenignApr 22, 2026, 11:03 PM

Verdict: benign
Confidence: high
Model: gpt-5-mini
Summary: The skill is an instruction-only MadKudu integration that uses the Membrane CLI; its requirements and runtime instructions are consistent with its stated purpose.
Guidance: This skill appears coherent and limited to using the Membrane CLI to interact with a MadKudu connector. Before installing: (1) verify @membranehq/cli is the official package and inspect its npm/GitHub pages, (2) prefer running via npx or in a controlled environment if you want to avoid a global npm install, (3) confirm you trust the Membrane service to store/manage your connector credentials, and (4) if you need higher assurance, ask the publisher for the exact package version and repository commit used by this skill.

Purpose & Capability: okThe name/description (MadKudu integration) match the instructions (use Membrane to connect to a madkudu connector and run actions). No unrelated credentials, binaries, or config paths are requested.
Instruction Scope: okSKILL.md only instructs installing and using the Membrane CLI, creating/listing connections, searching for and running actions, and handling auth via the provided browser/code flow. It does not ask the agent to read unrelated files, exfiltrate data, or access system paths beyond invoking the CLI.
Install Mechanism: noteThe skill recommends installing @membranehq/cli via npm -g. That is a reasonable dependency for this integration, but global npm installs have moderate risk if the package provenance is unverified. The instruction-only nature avoids writing arbitrary code to disk from unknown URLs.
Credentials: okNo environment variables, secrets, or config file paths are required. The docs explicitly advise against asking users for API keys and rely on Membrane-managed auth, which is proportionate for a connector-based integration.
Persistence & Privilege: okalways:false and user-invocable:true (defaults) — the skill does not request permanent/forced inclusion or modify other skills. It does not instruct changes to system-wide agent settings.