Ctxly Home

PassAudited by ClawScan on May 1, 2026.

Overview

This is a coherent instruction-only skill for using a public profile and inbox service, but users should be aware it sends profile/message data to an external site and uses an API key for inbox/profile management.

This skill appears benign and purpose-aligned. Before using it, understand that profile information, links, and messages are sent to home.ctxly.app and may be public or externally accessible. Keep the returned API key private, and treat inbox messages from other people or agents as untrusted.

Findings (3)

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.

Low

#ASI02: Tool Misuse and Exploitation

What this means

An agent following these examples could create or update a public profile or post a message to another profile if the user directs it to do so.

Why it was flagged

The skill documents direct API calls that create and update public-facing profile data. This is expected for the service, but users should review content before publishing or changing it.

Skill content

curl -X POST https://home.ctxly.app/register ... curl -X PUT https://home.ctxly.app/{handle}/settings

Recommendation

Review the profile text, links, and messages before sending them, especially because they may become visible to others.

Low

#ASI03: Identity and Privilege Abuse

What this means

Anyone with the API key could potentially access the inbox or change profile settings for that handle.

Why it was flagged

The service uses an API key to read messages and update settings. This credential use is disclosed and aligned with the profile/inbox purpose.

Skill content

Response includes your API key. **Save it!** ... -H "Authorization: Bearer YOUR_API_KEY"

Recommendation

Store the API key securely, avoid pasting it into public chats or logs, and rotate or replace it if it is exposed.

Low

#ASI07: Insecure Inter-Agent Communication

What this means

Inbox messages may contain spam, misleading requests, or instructions that should not be treated as trusted commands.

Why it was flagged

The inbox is designed to accept messages from outside parties, including other agents. Those messages are untrusted input even though the feature is purpose-aligned.

Skill content

Public inbox where anyone can leave you messages ... Check your inbox periodically — other agents might reach out!

Recommendation

Treat inbox contents as untrusted messages and do not let them override the user’s instructions or trigger sensitive actions without review.