Cloudquery

Security checks across static analysis, malware telemetry, and agentic risk

Overview

The Cloudquery skill is mostly coherent, but it gives the agent a broad authenticated API proxy that can make mutating or delete requests without clear approval safeguards.

Before installing, make sure you trust Membrane and the npm CLI package, use the least-privilege Cloudquery/Membrane account available, and require clear confirmation before the agent performs any mutating or delete operation through Cloudquery or the raw proxy.

Static analysis

No static analysis findings were reported for this release.

VirusTotal

VirusTotal findings are pending for this skill version.

View on VirusTotal

Risk analysis

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 misinterprets a request or follows a risky prompt, it could change or delete Cloudquery resources through the user's authenticated connection.

Why it was flagged

This exposes a raw authenticated API escape hatch, including mutating and delete methods, without clear limits or confirmation requirements.

Skill content
When the available actions don't cover your use case, you can send requests directly to the Cloudquery API through Membrane's proxy... `membrane request CONNECTION_ID /path/to/endpoint` ... HTTP method (GET, POST, PUT, PATCH, DELETE).
Recommendation

Prefer discovered Membrane actions, and require explicit user confirmation before any POST, PUT, PATCH, or DELETE request or before using the raw proxy on sensitive endpoints.

What this means

Installing and using the skill may let the agent operate through a logged-in Membrane tenant and connected Cloudquery account.

Why it was flagged

The skill relies on delegated Membrane/Cloudquery authentication and credential refresh. This is disclosed and purpose-aligned, but it is sensitive account authority.

Skill content
Membrane handles authentication and credentials refresh automatically... `membrane login --tenant --clientName=<agentType>`
Recommendation

Use a least-privilege account or tenant where possible, verify the connection before use, and revoke the Membrane connection when it is no longer needed.

What this means

The behavior of the installed CLI can change over time depending on the npm package version resolved at install time.

Why it was flagged

The setup pulls the latest Membrane CLI package globally from npm. This is a normal setup path for the stated purpose, but it is unpinned remote code.

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

Install from the official package source, consider pinning a known version, and review npm/package provenance if using this in a sensitive environment.

What this means

Cloudquery queries, responses, and authenticated requests may pass through Membrane infrastructure.

Why it was flagged

Cloudquery API traffic and authentication are routed through Membrane as a gateway. This is disclosed and central to the integration, but users should understand the data boundary.

Skill content
send requests directly to the Cloudquery API through Membrane's proxy... injects the correct authentication headers
Recommendation

Use this only if you trust Membrane for the relevant Cloudquery data, and avoid sending unnecessary sensitive data through proxy requests.