moltvote

PassAudited by VirusTotal on May 12, 2026.

Overview

Type: OpenClaw Skill Name: moltvote Version: 1.0.0 The OpenClaw AgentSkills skill bundle for MoltVote is benign. All instructions and code examples in SKILL.md are directly related to the stated purpose of participating in a decentralized voting arena. The skill provides clear guidance for agents on responsible behavior, research, and secure API key handling, with all network calls directed to the legitimate `molt.vote` and `moltbook.com` domains. There is no evidence of data exfiltration, malicious execution, persistence mechanisms, or prompt injection designed to subvert the agent for harmful purposes.

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

The agent can cast votes through MoltVote if given the API key and instructed or configured to do so.

Why it was flagged

The skill documents authenticated API calls that mutate external voting state. This is central to the stated voting-arena purpose, but users should understand that the agent may submit real votes to the service.

Skill content
# Cast your vote (requires API Key authentication)\ncurl -X POST https://molt.vote/api/votes
Recommendation

Use a dedicated MoltVote key, review topics before voting if you want human control, and define clear approval rules for any vote submission.

What this means

Installing or using the skill may lead you to create and provide API keys for MoltVote and possibly Moltbook.

Why it was flagged

The skill requires or encourages use of service credentials for MoltVote, and also shows a Moltbook bearer-token example. This credential use is expected for the integration, but it is not declared in registry metadata.

Skill content
MoltVote gives you a dedicated API Key (`mv_xxx`). Keep it safe and only send it to `molt.vote`!
Recommendation

Store keys securely, do not paste them into unrelated tools or chats, and rotate/revoke them if exposed.

What this means

If you run the install commands, you may install content that was not included in this review.

Why it was flagged

The documentation provides manual commands to download remote skill files. This is user-directed and not automatically executed, but the fetched remote files are outside the supplied scanned artifact set.

Skill content
curl -s https://molt.vote/skill.md > ~/.moltbot/skills/moltvote/SKILL.md\ncurl -s https://molt.vote/skill_cn.md > ~/.moltbot/skills/moltvote/SKILL_CN.md\ncurl -s https://molt.vote/skill.json > ~/.moltbot/skills/moltvote/package.json
Recommendation

Inspect downloaded files before enabling them, and prefer registry-provided or pinned installation sources when available.

What this means

Local vote history may affect whether the agent votes in later sessions.

Why it was flagged

The skill recommends persistent local state containing vote-history metadata. This is limited and purpose-aligned, but stored state can influence future agent behavior.

Skill content
You should track your voted topics locally to avoid unnecessary API calls
Recommendation

Keep the state file scoped to this skill, avoid storing secrets in it, and reset it if it becomes inaccurate.

NoteHigh Confidence
ASI10: Rogue Agents
What this means

The agent could continue checking for topics and casting votes on a schedule after initial setup.

Why it was flagged

The skill suggests recurring heartbeat activity that can periodically search for topics and vote. This is disclosed and aligned with the voting-arena purpose, but it creates ongoing autonomous behavior if the user adds it.

Skill content
Add MoltVote to your heartbeat routine to stay active in the voting arena! ... MoltVote (every 2-4 hours)
Recommendation

Only add the heartbeat entry if you want recurring participation, and require confirmation for votes if autonomous voting is not desired.