Mslm Cloud

ReviewAudited by ClawScan on May 10, 2026.

Overview

This appears to be a real Mslm Cloud integration, but it gives the agent broad authenticated API access, including changing or deleting cloud resources, with limited built-in scoping.

Install only if you are comfortable giving Membrane-mediated access to your Mslm Cloud account. Use a least-privileged account where possible, confirm any write/delete or user-organization changes before execution, and consider pinning the Membrane CLI version rather than using @latest.

Findings (4)

Artifact-based informational review of SKILL.md, metadata, install specs, static scan signals, and capability signals. ClawScan does not execute the skill or run runtime probes.

What this means

If the agent uses this too broadly or on the wrong connection, it could change or delete Mslm Cloud data, users, organizations, files, or sharing settings.

Why it was flagged

This documents a broad authenticated API escape hatch, including mutating and deleting requests, without clear confirmation, scope, or rollback guidance.

Skill content
When the available actions don't cover your use case, you can send requests directly to the Mslm Cloud API through Membrane's proxy... `-X, --method` | HTTP method (GET, POST, PUT, PATCH, DELETE).
Recommendation

Prefer scoped prebuilt actions, require explicit user confirmation before POST/PUT/PATCH/DELETE or user/org changes, and verify the exact connection, endpoint, and payload before running raw proxy requests.

What this means

The agent may act with the permissions of the connected Mslm Cloud/Membrane account.

Why it was flagged

The integration uses delegated account credentials and automatic refresh. That is expected for Mslm Cloud access, but it gives the agent ongoing authenticated authority through Membrane.

Skill content
Membrane handles authentication and credentials refresh automatically... Membrane automatically... injects the correct authentication headers — including transparent credential refresh if they expire.
Recommendation

Authenticate only the intended account, use the least-privileged account or connection available, and revoke the Membrane connection when no longer needed.

What this means

A future CLI release or npm supply-chain issue could affect what is executed locally.

Why it was flagged

The documented setup installs the latest Membrane CLI globally from npm, so the exact code run can change over time.

Skill content
npm install -g @membranehq/cli@latest
Recommendation

Install from the official package source, consider pinning a reviewed CLI version, and avoid running global installs in highly sensitive environments without review.

What this means

Remote setup instructions could influence how the agent proceeds if treated as authoritative.

Why it was flagged

The skill may expose service-provided instructions to the agent during connection setup. This can be useful, but such text should not override the user's actual request or safety constraints.

Skill content
`clientAction.agentInstructions` (optional) — instructions for the AI agent on how to proceed programmatically.
Recommendation

Treat returned agent instructions as advisory data, and keep user intent, approval requirements, and safety rules authoritative.