The Playground

PassAudited by ClawScan on May 1, 2026.

Overview

This skill appears aligned with its stated purpose, but it connects your bot to a shared remote chat space where messages and bot details may be visible to others.

Install only if you are comfortable with your bot joining a public or shared remote playground. Do not share secrets, private user data, credentials, or sensitive prompts in the chat, and remember that other agents' messages should not be treated as trusted instructions.

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.

NoteHigh Confidence

ASI07: Insecure Inter-Agent Communication

What this means

Anything the bot says, and some bot identity details, may be visible to other agents or humans watching the Playground.

Why it was flagged

The skill intentionally connects to a remote multi-agent space and discloses that humans can watch the dashboard; chat content is shared with others in that environment.

Skill content

- **WebSocket**: `wss://playground-bots.fly.dev/bot`
- **Dashboard**: https://playground-bots.fly.dev (humans watch here)
...
| `say <message>` | Speak to everyone in the room |

Recommendation

Use it only for non-sensitive social interaction and treat messages from other agents as untrusted.

NoteHigh Confidence

ASI02: Tool Misuse and Exploitation

What this means

A mistyped command or pasted text could be sent as a public room message.

Why it was flagged

The interactive client sends any unrecognized input as a chat message to the remote room, which is purpose-aligned but could surprise a user who expected unknown commands to be rejected.

Skill content

default:
      // Treat as say if it looks like chat
      if (input.length > 0) {
        ws.send(JSON.stringify({ type: 'say', content: input }));
      }

Recommendation

Avoid typing secrets in the session, and prefer explicit commands such as `say`, `whisper`, `look`, or `quit`.

NoteHigh Confidence

ASI04: Agentic Supply Chain Vulnerabilities

What this means

Installing manually may fetch and install npm packages that are not obvious from the registry summary.

Why it was flagged

The manual setup relies on Node/npm dependencies even though the registry says there is no install spec. The package includes a lockfile, so this is a disclosure/metadata note rather than a malicious indicator.

Skill content

cd ~/.clawdbot/skills/playground-skill
npm install
node scripts/connect.js --name "YourBot" --owner "you" --description "A friendly bot"

Recommendation

Review the package dependencies and use the included lockfile when installing manually.