Rd Station
ReviewAudited by ClawScan on May 10, 2026.
Overview
This looks like a legitimate RD Station/Membrane integration, but it gives the agent broad authenticated power to change or delete CRM data without clear approval or scoping rules in the provided text.
Review this before installing if your RD Station account contains important CRM or marketing data. Prefer read-only or limited permissions where possible, require confirmation before any create/update/delete operation, and be cautious with raw proxy requests or broad actions that are not tied to a specific user-approved record.
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.
An agent could accidentally modify or delete RD Station CRM/marketing data if it chooses the wrong action, endpoint, or parameters.
The skill gives the agent a raw authenticated API escape hatch, including destructive or mutating methods, without showing clear user-approval or scoping safeguards in the provided artifact.
When the available actions don't cover your use case, you can send requests directly to the RD Station API through Membrane's proxy... `--method` | HTTP method (GET, POST, PUT, PATCH, DELETE).
Require explicit user confirmation for create/update/delete actions, prefer discovered scoped actions over raw proxy calls, preview targeted records, and document rollback or recovery expectations.
Actions run through this skill may use the user's connected RD Station account and its permissions.
The skill relies on delegated Membrane/RD Station credentials and automatic refresh, which is expected for the integration but gives the agent account-backed authority.
Membrane handles authentication and credentials refresh automatically... `membrane login --tenant --clientName=<agentType>`
Use a least-privileged RD Station/Membrane connection where possible, review connected-account permissions, and revoke the connection when no longer needed.
The local CLI behavior can change over time as @latest changes, and global npm installs execute code from the package source.
The setup uses a globally installed npm CLI with the moving @latest tag. This is central to the skill's purpose, but the exact executable version is not pinned.
npm install -g @membranehq/cli@latest
Install the CLI only from the trusted npm package, consider pinning a reviewed version, and update deliberately.
RD Station request data and responses may pass through Membrane while the integration is used.
The skill discloses a third-party gateway/proxy data path for authenticated RD Station requests. This is purpose-aligned, but users should be aware of the data boundary.
send requests directly to the RD Station API through Membrane's proxy. Membrane automatically appends the base URL... and injects the correct authentication headers
Use this only for RD Station data you are comfortable processing through Membrane, and review Membrane's account, logging, and data-handling settings.