Linear
Security checks across malware telemetry and agentic risk
Overview
This is a coherent Linear integration, but it gives the agent broad authenticated ability to create, update, delete, and generate Linear actions without explicit confirmation guardrails.
Install only if you are comfortable connecting Membrane to your Linear workspace. Confirm every create, update, delete, or generated action before it runs, use the least-privileged Linear access available, consider pinning the CLI version, and revoke the connection when finished.
VirusTotal
65/65 vendors flagged this skill as clean.
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.
If the agent interprets a request too broadly, it could change or delete Linear issues or projects in the connected workspace.
The skill exposes generic action execution for actions that can create, update, comment on, or delete Linear business data, but it does not instruct the agent to obtain explicit confirmation before mutating or deleting data.
Use action names and parameters as needed... Delete Issue | delete-issue | Deletes an issue from Linear (moves to trash)... Update Issue... Create Project... membrane action run <actionId> --connectionId=CONNECTION_ID --json
Require explicit user approval before running create, update, delete, comment, or other mutating Linear actions, and confirm the exact target workspace, project, issue, and input parameters.
A newly generated action could have broader or different effects than the user expected, especially when run with authenticated Linear access.
The skill allows dynamically generated remote actions to be created and then run against the Linear connection, without a stated review or approval step for the generated action's behavior.
If no suitable action exists, describe what you want — Membrane will build it automatically... READY — action is fully built. Proceed to running it.
Before running generated actions, inspect the action description, input schema, and intended effects, and ask the user to approve any action that changes Linear data.
The agent can act through the connected Linear account according to the permissions granted during authentication.
The integration requires authenticating to Membrane and connecting a Linear account with delegated access. This is expected for a Linear integration, but it grants ongoing account authority.
Membrane handles authentication and credentials refresh automatically... membrane login --tenant --clientName=<agentType>... membrane connect --connectorKey linear
Use the least-privileged Linear account or connection available, review granted permissions, and revoke the Membrane/Linear connection when it is no longer needed.
The installed CLI version may change over time, and a global install affects the user's local environment.
The setup uses a global npm install of the latest Membrane CLI. This is central to the skill's purpose, but the version is unpinned and the registry metadata has no install spec.
npm install -g @membranehq/cli@latest
Prefer a pinned, trusted CLI version where possible and install it only from the expected npm package source.