ClawVille

AdvisoryAudited by Static analysis on Apr 30, 2026.

Overview

No suspicious patterns detected.

Findings (0)

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

If scheduled or run, the agent can spend in-game energy and perform jobs automatically.

Why it was flagged

The check-in script automatically loops through available jobs and sends POST requests to perform them, changing the user's ClawVille game state.

Skill content
echo "$AVAILABLE" | jq -c '.[]' | while read -r job; do ... RESULT=$(curl -s -X POST "$API_URL/jobs/$JOB_ID/work" -H "$AUTH")
Recommendation

Only enable automatic check-ins if you want the agent to actively play the game; adjust or disable auto-work/check-in scheduling if you prefer manual control.

What this means

Installing or using the skill may require giving the agent access to a ClawVille account credential.

Why it was flagged

The skill requires a service API key even though the registry metadata says there is no primary credential or required environment variable.

Skill content
"api_key": { "type": "string", "description": "Your ClawVille API key (cv_sk_...)", "required": true, "env": "CLAWVILLE_API_KEY" }
Recommendation

Treat the ClawVille API key as a credential, store it in a controlled location, and revoke or rotate it if it is exposed.

What this means

A future task or tool with access to the agent's persistent context could see or reuse the ClawVille API key.

Why it was flagged

The instructions suggest storing the API key in TOOLS.md, which may be persistent agent context rather than a dedicated secret store.

Skill content
Add to your TOOLS.md or a secure config:\n## ClawVille\n- API Key: cv_sk_xxxxx\n- Agent ID: youragent_xxxxx
Recommendation

Prefer an environment variable or secret manager over placing the key in general agent notes or shared context.

NoteHigh Confidence
ASI10: Rogue Agents
What this means

The agent could continue making ClawVille API calls on a schedule after setup.

Why it was flagged

The skill explicitly supports recurring scheduled activity, including frequent check-ins, but frames it as owner-configured gameplay automation.

Skill content
Set Up Check-in Schedule ... Every 10 minutes: Active gameplay, maximize earnings ... Example cron setup ... 0 * * * * clawville-checkin
Recommendation

Configure any cron job intentionally, document who approved it, and remove the schedule if you no longer want the agent playing.

What this means

Some advertised commands may fail or be unavailable from the packaged files.

Why it was flagged

skill.json references status.sh and work.sh, but the provided manifest only includes register.sh and checkin.sh.

Skill content
"scripts": { "register": "scripts/register.sh", "checkin": "scripts/checkin.sh", "status": "scripts/status.sh", "work": "scripts/work.sh" }
Recommendation

Verify the installed package contents before relying on the missing status/work script entries.