Posthog
ReviewAudited by ClawScan on May 10, 2026.
Overview
This looks like a legitimate PostHog integration, but using it grants Membrane/PostHog access and may allow changes to analytics settings.
Install this skill only if you trust Membrane and the npm CLI package. Use a least-privilege PostHog connection, review write actions before approving them, and revoke the connection when you no longer need the integration.
Findings (5)
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 used with a privileged PostHog connection, the agent could make changes that affect analytics configuration or product behavior such as feature flags.
The skill is not read-only; it advertises actions that can create or update PostHog project resources.
PostHog integration. Manage Persons, Groups, Events, Experiments, Dashboards, Annotations ... Create Feature Flag ... Update Dashboard ... Update Cohort
Use least-privilege PostHog access and require explicit user confirmation before create, update, or delete actions.
Installing and using the skill may grant access to PostHog account data such as persons, events, experiments, and dashboards.
The skill requires delegated authentication and ongoing credential refresh through Membrane.
Membrane handles authentication and credentials refresh automatically ... membrane login --tenant --clientName=<agentType>
Connect only the intended PostHog project, prefer least-privilege credentials, and revoke the Membrane/PostHog connection when no longer needed.
The user must trust the npm package and Membrane CLI behavior, including future latest-version changes.
The skill depends on an external npm CLI installed globally at the latest version; that code is not included in the reviewed artifact set.
npm install -g @membranehq/cli@latest
Install only from the trusted npm publisher, consider pinning a reviewed CLI version, and avoid running it in sensitive environments unless needed.
Remote provider guidance could influence the agent's next steps during setup if not treated carefully.
The skill allows remote setup responses to provide instructions to the agent.
`clientAction.agentInstructions` (optional) — instructions for the AI agent on how to proceed programmatically.
Treat remote agentInstructions as lower-priority setup hints and do not let them override the user's intent, security rules, or approval requirements.
PostHog authentication state and requests depend on Membrane's service boundary and account permissions.
PostHog access is mediated through Membrane rather than only direct local calls to PostHog.
This skill uses the Membrane CLI to interact with PostHog. Membrane handles authentication and credentials refresh automatically
Review Membrane's access model and connect only accounts and projects that the agent should use.