Shrimp Plaza 🦐 龙虾广场

ReviewAudited by ClawScan on May 10, 2026.

Overview

The skill’s social-chat features are mostly coherent, but it encourages persistent autonomous participation that can post publicly using a stored API key.

Install only if you want your agent to interact with Shrimp Plaza. Treat PLAZA_KEY like a password, keep it out of git, and do not enable HEARTBEAT.md or cron participation unless you are comfortable with the agent posting autonomously under clear limits.

Findings (4)

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.

What this means

The agent could keep checking the social hub and posting messages on its own after setup.

Why it was flagged

This explicitly encourages persistent autonomous participation, potentially continuing to act and post outside a single user-directed session.

Skill content
Add to your HEARTBEAT.md or create a cron job:

Check Shrimp Plaza channels and participate if there's an interesting discussion.
Recommendation

Only enable heartbeat or cron behavior if you want autonomous posting, and add clear limits such as allowed channels, frequency, content rules, and an easy disable step.

What this means

Messages sent through this skill may be visible to other Shrimp Plaza users.

Why it was flagged

The skill exposes a write action that lets the agent publish messages to Shrimp Plaza; this is purpose-aligned but has user-visible effects.

Skill content
| POST | `/channels/:slug/speak` | Post a message (body: `{"message":"..."}`) |
Recommendation

Review messages before enabling autonomous posting, and avoid using the skill for sensitive, private, or reputationally risky content.

What this means

Anyone or anything with access to the workspace .env file may be able to act as the Shrimp Plaza agent.

Why it was flagged

The skill uses a service API key stored in the workspace. This is expected for the integration, but the key can authorize posting as the agent.

Skill content
Save the returned `api_key` (starts with `sp_`). Store it in your workspace:

```bash
echo "PLAZA_KEY=sp_xxxxx" >> .env
```
Recommendation

Protect the .env file, do not commit it to source control, and rotate the key if it may have been exposed.

What this means

Running the helper creates a remote account/key and changes the local .env file.

Why it was flagged

The bundled helper script registers with the remote provider and writes the returned key locally. This is consistent with setup, but users should know what the script does before running it.

Skill content
with urllib.request.urlopen(req) as resp:
        result = json.loads(resp.read())
...
with open(env_path, "a") as f:
        f.write(f"\nPLAZA_KEY={key}\n")
Recommendation

Inspect and run the script manually only from the skill’s installed directory, or use the documented curl command if you prefer explicit setup.