Casino Bot Builder

PassAudited by VirusTotal on May 11, 2026.

Overview

Type: OpenClaw Skill Name: rollhub-bot-builder Version: 1.0.0 The skill bundle provides functional templates and a setup script for building gambling bots on Telegram, Discord, and Twitter using the Agent Casino API (agent.rollhub.com). The code in scripts/setup-bot.sh and the reference files (telegram-bot.md, discord-bot.md, twitter-bot.md) aligns with the stated purpose and contains no evidence of data exfiltration, backdoors, or malicious prompt injection. A hardcoded referral ID (ref_27fcab61) is present in all registration calls, which is a common affiliate marketing practice rather than a security threat.

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

Anyone who can mention the Twitter bot in the expected format could cause it to wager the bot owner’s casino balance and post replies from the account.

Why it was flagged

The Twitter reply mode turns public mentions into casino API bets without an allowlist, confirmation step, per-user limit, or stop-loss control.

Skill content
def reply_betting():
    """Monitor mentions and place bets from replies."""
    ...
                amount = float(parts[-1])
    ...
                result = place_bet(game, amount, **kwargs)
Recommendation

Add explicit authorized-user allowlists, per-bet and daily caps, confirmations for spending, rate limits, and stop-loss/kill-switch controls before using public reply-based betting.

ConcernHigh Confidence
ASI08: Cascading Failures
What this means

A typo or unauthorized command could rapidly create many bets and drain the bot’s available balance.

Why it was flagged

A user-supplied rounds value fans out into repeated casino API bet calls, with no hard maximum, delay, max-loss check, or target-profit stop in the Telegram template.

Skill content
game, amount, rounds = context.args[0], float(context.args[1]), int(context.args[2])
...
for i in range(rounds):
    ...
    result = place_bet(game, amount, **kwargs)
Recommendation

Enforce hard maximum rounds and amounts, add delays, require owner approval for autoplay, and implement max-loss/target-profit stopping logic in code.

What this means

Users may underestimate the account authority they are granting; compromise or misuse of these tokens could allow public posting and wagering from shared accounts.

Why it was flagged

The templates require sensitive credentials that authorize public social-account actions and casino betting, while the registry metadata declares no required environment variables or primary credential.

Skill content
TWITTER_API_KEY=your_key
TWITTER_API_SECRET=your_secret
TWITTER_ACCESS_TOKEN=your_token
TWITTER_ACCESS_SECRET=your_token_secret
AGENT_CASINO_API_KEY=your_api_key
Recommendation

Declare these credentials in metadata, use separate low-privilege bot accounts, keep only limited funds available, rotate tokens regularly, and avoid sharing one casino API key across untrusted users.

What this means

A user may believe the examples include safety controls that are not actually present in the provided code.

Why it was flagged

The documentation advertises safeguards, but the supplied autoplay examples do not implement max-loss/target-profit checks, and the Discord template does not show role checks before betting commands.

Skill content
Stop conditions: max loss, target profit, or round limit
...
- Role-based access control
Recommendation

Update the templates to implement the advertised controls or clearly state that users must add them before deployment.

ConcernHigh Confidence
ASI10: Rogue Agents
What this means

The bot can continue acting on new social inputs long after the initial command, creating ongoing financial and account-posting risk.

Why it was flagged

The template includes an indefinite autonomous loop that keeps monitoring mentions and can keep placing bets until the process is stopped.

Skill content
def reply_betting():
    """Monitor mentions and place bets from replies."""
    since_id = None
    while True:
Recommendation

Run only under supervision, add a clear shutdown mechanism, require owner-only control commands, and log/alert on every bet placed.

What this means

Future dependency versions may behave differently or introduce vulnerabilities.

Why it was flagged

The setup instructions rely on unpinned public package installs. This is expected for templates, but versions and provenance are not locked.

Skill content
echo "4. pip install python-telegram-bot requests"
...
echo "4. npm install discord.js axios"
...
echo "4. pip install tweepy requests"
Recommendation

Pin dependency versions, use lockfiles, and install from trusted package indexes.