Outfit

Security checks across malware telemetry and agentic risk

Overview

This looks like a legitimate Outfit integration, but it gives the agent broad authenticated API access that could change or delete Outfit account data without clear approval limits.

Review this skill before installing. It appears purpose-aligned for managing Outfit through Membrane, but only use it with a least-privileged account and require explicit user approval before any API call that creates, updates, deletes, changes settings, manages users, or affects billing.

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.

#
ASI02: Tool Misuse and Exploitation
Medium
What this means

The agent could make broad changes to Outfit data, settings, or records if a task is misunderstood or a prompt asks it to use the proxy directly.

Why it was flagged

The skill gives the agent a raw authenticated API escape hatch with mutating and deleting methods, without artifact-backed limits or confirmation requirements for high-impact actions.

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

Use this only for specific, user-approved tasks. Require explicit confirmation before POST, PUT, PATCH, or DELETE requests, and review the endpoint, method, and request body before running them.

#
ASI03: Identity and Privilege Abuse
Medium
What this means

Installing and using the skill can give the agent access through a connected Membrane/Outfit account, potentially with whatever permissions that account has.

Why it was flagged

The integration depends on delegated account credentials that may be refreshed automatically. This is expected for the stated purpose, but it is sensitive authority.

Skill content
Membrane handles authentication and credentials refresh automatically
Recommendation

Connect with the least-privileged Outfit account that can complete the task, review granted permissions, and revoke the connection when it is no longer needed.

#
ASI04: Agentic Supply Chain Vulnerabilities
Low
What this means

The behavior of the skill depends on whatever version of the Membrane CLI is current at install time.

Why it was flagged

The setup instructs a global install of the latest CLI package. This is central to the skill's purpose, but it is not pinned to a reviewed version.

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

Install only from a trusted npm environment, consider pinning a known CLI version, and review Membrane CLI provenance before use.

#
ASI07: Insecure Inter-Agent Communication
Low
What this means

Task data sent to Outfit through this workflow may also pass through Membrane infrastructure.

Why it was flagged

Outfit API traffic and authenticated requests are routed through Membrane as a proxy/gateway. This is disclosed and purpose-aligned, but it is an additional data and trust boundary.

Skill content
send requests directly to the Outfit API through Membrane's proxy. Membrane automatically appends the base URL to the path you provide and injects the correct authentication headers
Recommendation

Avoid sending unnecessary sensitive data, and ensure the user is comfortable with Membrane acting as the authenticated integration gateway.