Snapshot
Security checks across static analysis, malware telemetry, and agentic risk
Overview
The skill is a coherent Membrane-based SnapShot integration, but it asks the agent to install/use a CLI, authenticate, and make authenticated SnapShot API requests, including potentially mutating requests.
This appears to be a legitimate instruction-only SnapShot integration. Before installing, verify the Membrane CLI source, connect only the intended account, and require explicit approval before the agent performs write, delete, sharing, or bulk actions through the API proxy.
Static analysis
No static analysis findings were reported for this release.
VirusTotal
VirusTotal findings are pending for this skill version.
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.
Installing the CLI gives the package code access to run on the local machine under the user's account.
The skill asks the user to install a global npm CLI package using the latest tag. This is a disclosed, purpose-aligned setup step, but it depends on an external package source and a moving version.
npm install -g @membranehq/cli@latest
Install only from the official package source, consider pinning a reviewed version, and verify the Membrane CLI before use.
The agent may be able to act through the user's connected SnapShot account while the Membrane connection remains valid.
The skill uses authenticated Membrane/SnapShot access and automatic credential refresh. This is expected for the integration, but it is sensitive account authority.
Membrane handles authentication and credentials refresh automatically
Connect only the intended SnapShot account, review requested permissions during authentication, and revoke the connection when it is no longer needed.
An agent could make changes to SnapShot data, including updates or deletions, if the user asks for or permits such operations.
The skill documents a broad authenticated API escape hatch, including mutating and deleting methods. This is disclosed and related to the integration, but it can affect account data if used carelessly.
When the available actions don't cover your use case, you can send requests directly to the SnapShot API through Membrane's proxy... HTTP method (GET, POST, PUT, PATCH, DELETE)
Prefer discovered Membrane actions when possible, and require explicit user confirmation before POST, PUT, PATCH, DELETE, sharing, or bulk operations.
SnapShot request and response data may pass through Membrane as part of normal operation.
Requests to SnapShot are routed through Membrane's proxy, which is a third-party gateway handling request data and authentication headers. The data flow is disclosed and purpose-aligned.
send requests directly to the SnapShot API through Membrane's proxy
Avoid sending unnecessary sensitive screenshots, recordings, or metadata through the integration, and confirm Membrane is an acceptable intermediary for your organization.